Lin Wang

Qiufan Ji, Lin Wang, Cong Shi et al.

Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable to adversarial examples, threatening their practical deployment. Despite the many research endeavors have been made to tackle this issue in recent years, the diversity of adversarial examples on 3D point clouds makes them more challenging to defend against than those on 2D images. For examples, attackers can generate adversarial examples by adding, shifting, or removing points. Consequently, existing defense strategies are hard to counter unseen point cloud adversarial examples. In this paper, we first establish a comprehensive, and rigorous point cloud adversarial robustness benchmark to evaluate adversarial robustness, which can provide a detailed understanding of the effects of the defense and attack methods. We then collect existing defense tricks in point cloud adversarial defenses and then perform extensive and systematic experiments to identify an effective combination of these tricks. Furthermore, we propose a hybrid training augmentation methods that consider various types of point cloud adversarial examples to adversarial training, significantly improving the adversarial robustness. By combining these tricks, we construct a more robust defense framework achieving an average accuracy of 83.45\% against various attacks, demonstrating its capability to enabling robust learners. Our codebase are open-sourced on: \url{https://github.com/qiufan319/benchmark_pc_attack.git}.

Haotian Bai, Yuanhuiyi Lyu, Lutao Jiang et al.

Text-to-3D form plays a crucial role in creating editable 3D scenes for AR/VR. Recent advances have shown promise in merging neural radiance fields (NeRFs) with pre-trained diffusion models for text-to-3D object generation. However, one enduring challenge is their inadequate capability to accurately parse and regenerate consistent multi-object environments. Specifically, these models encounter difficulties in accurately representing quantity and style prompted by multi-object texts, often resulting in a collapse of the rendering fidelity that fails to match the semantic intricacies. Moreover, amalgamating these elements into a coherent 3D scene is a substantial challenge, stemming from generic distribution inherent in diffusion models. To tackle the issue of 'guidance collapse' and further enhance scene consistency, we propose a novel framework, dubbed CompoNeRF, by integrating an editable 3D scene layout with object-specific and scene-wide guidance mechanisms. It initiates by interpreting a complex text into the layout populated with multiple NeRFs, each paired with a corresponding subtext prompt for precise object depiction. Next, a tailored composition module seamlessly blends these NeRFs, promoting consistency, while the dual-level text guidance reduces ambiguity and boosts accuracy. Noticeably, our composition design permits decomposition. This enables flexible scene editing and recomposition into new scenes based on the edited layout or text prompts. Utilizing the open-source Stable Diffusion model, CompoNeRF generates multi-object scenes with high fidelity. Remarkably, our framework achieves up to a \textbf{54\%} improvement by the multi-view CLIP score metric. Our user study indicates that our method has significantly improved semantic accuracy, multi-view consistency, and individual recognizability for multi-object scene generation.

Jinjing Zhu, Yunhao Luo, Xu Zheng et al.

In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic segmentation?" Accordingly, we propose an online knowledge distillation (KD) framework that can simultaneously learn compact yet effective CNN-based and ViT-based models with two key technical breakthroughs to take full advantage of CNNs and ViT while compensating their limitations. Firstly, we propose heterogeneous feature distillation (HFD) to improve students' consistency in low-layer feature space by mimicking heterogeneous features between CNNs and ViT. Secondly, to facilitate the two students to learn reliable knowledge from each other, we propose bidirectional selective distillation (BSD) that can dynamically transfer selective knowledge. This is achieved by 1) region-wise BSD determining the directions of knowledge transferred between the corresponding regions in the feature space and 2) pixel-wise BSD discerning which of the prediction knowledge to be transferred in the logit space. Extensive experiments on three benchmark datasets demonstrate that our proposed framework outperforms the state-of-the-art online distillation methods by a large margin, and shows its efficacy in learning collaboratively between ViT-based and CNN-based models.

Xu Zheng, Tianbo Pan, Yunhao Luo et al.

Endeavors have been recently made to transfer knowledge from the labeled pinhole image domain to the unlabeled panoramic image domain via Unsupervised Domain Adaptation (UDA). The aim is to tackle the domain gaps caused by the style disparities and distortion problem from the non-uniformly distributed pixels of equirectangular projection (ERP). Previous works typically focus on transferring knowledge based on geometric priors with specially designed multi-branch network architectures. As a result, considerable computational costs are induced, and meanwhile, their generalization abilities are profoundly hindered by the variation of distortion among pixels. In this paper, we find that the pixels' neighborhood regions of the ERP indeed introduce less distortion. Intuitively, we propose a novel UDA framework that can effectively address the distortion problems for panoramic semantic segmentation. In comparison, our method is simpler, easier to implement, and more computationally efficient. Specifically, we propose distortion-aware attention (DA) capturing the neighboring pixel distribution without using any geometric constraints. Moreover, we propose a class-wise feature aggregation (CFA) module to iteratively update the feature representations with a memory bank. As such, the feature similarity between two domains can be consistently optimized. Extensive experiments show that our method achieves new state-of-the-art performance while remarkably reducing 80% parameters.

Xu Zheng, Yexin Liu, Yunfan Lu et al.

Event cameras are bio-inspired sensors that capture the per-pixel intensity changes asynchronously and produce event streams encoding the time, pixel position, and polarity (sign) of the intensity changes. Event cameras possess a myriad of advantages over canonical frame-based cameras, such as high temporal resolution, high dynamic range, low latency, etc. Being capable of capturing information in challenging visual conditions, event cameras have the potential to overcome the limitations of frame-based cameras in the computer vision and robotics community. In very recent years, deep learning (DL) has been brought to this emerging field and inspired active research endeavors in mining its potential. However, there is still a lack of taxonomies in DL techniques for event-based vision. We first scrutinize the typical event representations with quality enhancement methods as they play a pivotal role as inputs to the DL models. We then provide a comprehensive survey of existing DL-based methods by structurally grouping them into two major categories: 1) image/video reconstruction and restoration; 2) event-based scene understanding and 3D vision. We conduct benchmark experiments for the existing methods in some representative research directions, i.e., image reconstruction, deblurring, and object recognition, to identify some critical insights and problems. Finally, we have discussions regarding the challenges and provide new perspectives for inspiring more research studies.

Xu Zheng, Yunhao Luo, Chong Fu et al.

The popular methods for semi-supervised semantic segmentation mostly adopt a unitary network model using convolutional neural networks (CNNs) and enforce consistency of the model's predictions over perturbations applied to the inputs or model. However, such a learning paradigm suffers from two critical limitations: a) learning the discriminative features for the unlabeled data; b) learning both global and local information from the whole image. In this paper, we propose a novel Semi-supervised Learning (SSL) approach, called Transformer-CNN Cohort (TCC), that consists of two students with one based on the vision transformer (ViT) and the other based on the CNN. Our method subtly incorporates the multi-level consistency regularization on the predictions and the heterogeneous feature spaces via pseudo-labeling for the unlabeled data. First, as the inputs of the ViT student are image patches, the feature maps extracted encode crucial class-wise statistics. To this end, we propose class-aware feature consistency distillation (CFCD) that first leverages the outputs of each student as the pseudo labels and generates class-aware feature (CF) maps for knowledge transfer between the two students. Second, as the ViT student has more uniform representations for all layers, we propose consistency-aware cross distillation (CCD) to transfer knowledge between the pixel-wise predictions from the cohort. We validate the TCC framework on Cityscapes and Pascal VOC 2012 datasets, which outperforms existing SSL methods by a large margin.

Hao Ai, Zidong cao, Yan-pei Cao et al.

Depth estimation from a monocular 360° image is a burgeoning problem owing to its holistic sensing of a scene. Recently, some methods, \eg, OmniFusion, have applied the tangent projection (TP) to represent a 360°image and predicted depth values via patch-wise regressions, which are merged to get a depth map with equirectangular projection (ERP) format. However, these methods suffer from 1) non-trivial process of merging plenty of patches; 2) capturing less holistic-with-regional contextual information by directly regressing the depth value of each pixel. In this paper, we propose a novel framework, \textbf{HRDFuse}, that subtly combines the potential of convolutional neural networks (CNNs) and transformers by collaboratively learning the \textit{holistic} contextual information from the ERP and the \textit{regional} structural information from the TP. Firstly, we propose a spatial feature alignment (\textbf{SFA}) module that learns feature similarities between the TP and ERP to aggregate the TP features into a complete ERP feature map in a pixel-wise manner. Secondly, we propose a collaborative depth distribution classification (\textbf{CDDC}) module that learns the \textbf{holistic-with-regional} histograms capturing the ERP and TP depth distributions. As such, the final depth values can be predicted as a linear combination of histogram bin centers. Lastly, we adaptively combine the depth predictions from ERP and TP to obtain the final depth map. Extensive experiments show that our method predicts\textbf{ more smooth and accurate depth} results while achieving \textbf{favorably better} results than the SOTA methods.

Zhenyu Wu, Lin Wang, Wei Wang et al.

Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset. To prove this conjecture, we proposed a novel yet effective adversarial trajectory-ensemble active learning (ATAL). Our contributions are three-fold: 1) Our proposed adversarial attack triggering uncertainty can conquer the overconfidence of existing active learning methods and accurately locate these uncertain pixels. {2)} Our proposed trajectory-ensemble uncertainty estimation method maintains the advantages of the ensemble networks while significantly reducing the computational cost. {3)} Our proposed relationship-aware diversity sampling algorithm can conquer oversampling while boosting performance. Experimental results show that our ATAL can find such a point-labeled dataset, where a saliency model trained on it obtained $97\%$ -- $99\%$ performance of its fully-supervised version with only ten annotated points per image.

Yusheng Wang, Yunfan Lu, Ye Gao et al.

Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the information from clear regions in adjacent frames for current frame deblurring. To realize this process, our idea is to detect the pixel-wise blur level of each frame and combine it with video deblurring. To this end, we propose a novel framework that utilizes the motion magnitude prior (MMP) as guidance for efficient deep video deblurring. Specifically, as the pixel movement along its trajectory during the exposure time is positively correlated to the level of motion blur, we first use the average magnitude of optical flow from the high-frequency sharp frames to generate the synthetic blurry frames and their corresponding pixel-wise motion magnitude maps. We then build a dataset including the blurry frame and MMP pairs. The MMP is then learned by a compact CNN by regression. The MMP consists of both spatial and temporal blur level information, which can be further integrated into an efficient recurrent neural network (RNN) for video deblurring. We conduct intensive experiments to validate the effectiveness of the proposed methods on the public datasets.

Lin Wang, YongXin Guo, Tao Lin et al.

Partial client participation has been widely adopted in Federated Learning (FL) to reduce the communication burden efficiently. However, an inadequate client sampling scheme can lead to the selection of unrepresentative subsets, resulting in significant variance in model updates and slowed convergence. Existing sampling methods are either biased or can be further optimized for faster convergence.In this paper, we present DELTA, an unbiased sampling scheme designed to alleviate these issues. DELTA characterizes the effects of client diversity and local variance, and samples representative clients with valuable information for global model updates. In addition, DELTA is a proven optimal unbiased sampling scheme that minimizes variance caused by partial client participation and outperforms other unbiased sampling schemes in terms of convergence. Furthermore, to address full-client gradient dependence,we provide a practical version of DELTA depending on the available clients' information, and also analyze its convergence. Our results are validated through experiments on both synthetic and real-world datasets.

Jinjing Zhu, Haotian Bai, Lin Wang

Endeavors have been recently made to leverage the vision transformer (ViT) for the challenging unsupervised domain adaptation (UDA) task. They typically adopt the cross-attention in ViT for direct domain alignment. However, as the performance of cross-attention highly relies on the quality of pseudo labels for targeted samples, it becomes less effective when the domain gap becomes large. We solve this problem from a game theory's perspective with the proposed model dubbed as PMTrans, which bridges source and target domains with an intermediate domain. Specifically, we propose a novel ViT-based module called PatchMix that effectively builds up the intermediate domain, i.e., probability distribution, by learning to sample patches from both domains based on the game-theoretical models. This way, it learns to mix the patches from the source and target domains to maximize the cross entropy (CE), while exploiting two semi-supervised mixup losses in the feature and label spaces to minimize it. As such, we interpret the process of UDA as a min-max CE game with three players, including the feature extractor, classifier, and PatchMix, to find the Nash Equilibria. Moreover, we leverage attention maps from ViT to re-weight the label of each patch by its importance, making it possible to obtain more domain-discriminative feature representations. We conduct extensive experiments on four benchmark datasets, and the results show that PMTrans significantly surpasses the ViT-based and CNN-based SoTA methods by +3.6% on Office-Home, +1.4% on Office-31, and +17.7% on DomainNet, respectively.

Xu Zheng, Jinjing Zhu, Yexin Liu et al.

The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular projection (ERP) and a lack of pixel-wise annotations. For this reason, some works treat the ERP and pinhole images equally and transfer knowledge from the pinhole to ERP images via unsupervised domain adaptation (UDA). However, they fail to handle the domain gaps caused by: 1) the inherent differences between camera sensors and captured scenes; 2) the distinct image formats (e.g., ERP and pinhole images). In this paper, we propose a novel yet flexible dual-path UDA framework, DPPASS, taking ERP and tangent projection (TP) images as inputs. To reduce the domain gaps, we propose cross-projection and intra-projection training. The cross-projection training includes tangent-wise feature contrastive training and prediction consistency training. That is, the former formulates the features with the same projection locations as positive examples and vice versa, for the models' awareness of distortion, while the latter ensures the consistency of cross-model predictions between the ERP and TP. Moreover, adversarial intra-projection training is proposed to reduce the inherent gap, between the features of the pinhole images and those of the ERP and TP images, respectively. Importantly, the TP path can be freely removed after training, leading to no additional inference cost. Extensive experiments on two benchmarks show that our DPPASS achieves +1.06$\%$ mIoU increment than the state-of-the-art approaches.

Xu Zheng, Yunhao Luo, Pengyuan Zhou et al.

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the completely different characteristics of ViT and CNN and the long-existing capacity gap between teacher and student models in Knowledge Distillation (KD), directly transferring the cross-model knowledge is non-trivial. To this end, we subtly leverage the visual and linguistic-compatible feature character of ViT (i.e., student), and its capacity gap with the CNN (i.e., teacher) and propose a novel CNN-to-ViT KD framework, dubbed C2VKD. Importantly, as the teacher's features are heterogeneous to those of the student, we first propose a novel visual-linguistic feature distillation (VLFD) module that explores efficient KD among the aligned visual and linguistic-compatible representations. Moreover, due to the large capacity gap between the teacher and student and the inevitable prediction errors of the teacher, we then propose a pixel-wise decoupled distillation (PDD) module to supervise the student under the combination of labels and teacher's predictions from the decoupled target and non-target classes. Experiments on three semantic segmentation benchmark datasets consistently show that the increment of mIoU of our method is over 200% of the SoTA KD methods

Jiahang Cao, Xu Zheng, Yuanhuiyi Lyu et al.

The ability to detect objects in all lighting (i.e., normal-, over-, and under-exposed) conditions is crucial for real-world applications, such as self-driving.Traditional RGB-based detectors often fail under such varying lighting conditions.Therefore, recent works utilize novel event cameras to supplement or guide the RGB modality; however, these methods typically adopt asymmetric network structures that rely predominantly on the RGB modality, resulting in limited robustness for all-day detection. In this paper, we propose EOLO, a novel object detection framework that achieves robust and efficient all-day detection by fusing both RGB and event modalities. Our EOLO framework is built based on a lightweight spiking neural network (SNN) to efficiently leverage the asynchronous property of events. Buttressed by it, we first introduce an Event Temporal Attention (ETA) module to learn the high temporal information from events while preserving crucial edge information. Secondly, as different modalities exhibit varying levels of importance under diverse lighting conditions, we propose a novel Symmetric RGB-Event Fusion (SREF) module to effectively fuse RGB-Event features without relying on a specific modality, thus ensuring a balanced and adaptive fusion for all-day detection. In addition, to compensate for the lack of paired RGB-Event datasets for all-day training and evaluation, we propose an event synthesis approach based on the randomized optical flow that allows for directly generating the event frame from a single exposure image. We further build two new datasets, E-MSCOCO and E-VOC based on the popular benchmarks MSCOCO and PASCAL VOC. Extensive experiments demonstrate that our EOLO outperforms the state-of-the-art detectors,e.g.,RENet,by a substantial margin (+3.74% mAP50) in all lighting conditions.Our code and datasets will be available at https://vlislab22.github.io/EOLO/

Jiazhou Zhou, Xu Zheng, Yuanhuiyi Lyu et al.

In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular, due to the distinct modality gap with the image-text data and the lack of large-scale datasets, learning a common representation space for images, texts, and events is non-trivial.Intuitively, we need to address two key challenges: 1) how to generalize CLIP's visual encoder to event data while fully leveraging events' unique properties, e.g., sparsity and high temporal resolution; 2) how to effectively align the multi-modal embeddings, i.e., image, text, and events. Accordingly, we first introduce a novel event encoder that subtly models the temporal information from events and meanwhile, generates event prompts for modality bridging. We then design a text encoder that generates content prompts and utilizes hybrid text prompts to enhance EventBind's generalization ability across diverse datasets.With the proposed event encoder, text encoder, and image encoder, a novel Hierarchical Triple Contrastive Alignment (HTCA) module is introduced to jointly optimize the correlation and enable efficient knowledge transfer among the three modalities. We evaluate various settings, including fine-tuning and few-shot on three benchmarks, and our EventBind achieves new state-of-the-art accuracy compared with the previous methods, such as on N-Caltech101 (+5.34% and +1.70%) and N-Imagenet (+5.65% and +1.99%) with fine-tuning and 20-shot settings, respectively. Moreover, our EventBind can be flexibly extended to the event retrieval task using text or image queries, showing plausible performance. Project page:https://vlislab22.github.io/EventBind/.

Yunfan Lu, Zipeng Wang, Minjie Liu et al.

Event cameras sense the intensity changes asynchronously and produce event streams with high dynamic range and low latency. This has inspired research endeavors utilizing events to guide the challenging video superresolution (VSR) task. In this paper, we make the first attempt to address a novel problem of achieving VSR at random scales by taking advantages of the high temporal resolution property of events. This is hampered by the difficulties of representing the spatial-temporal information of events when guiding VSR. To this end, we propose a novel framework that incorporates the spatial-temporal interpolation of events to VSR in a unified framework. Our key idea is to learn implicit neural representations from queried spatial-temporal coordinates and features from both RGB frames and events. Our method contains three parts. Specifically, the Spatial-Temporal Fusion (STF) module first learns the 3D features from events and RGB frames. Then, the Temporal Filter (TF) module unlocks more explicit motion information from the events near the queried timestamp and generates the 2D features. Lastly, the SpatialTemporal Implicit Representation (STIR) module recovers the SR frame in arbitrary resolutions from the outputs of these two modules. In addition, we collect a real-world dataset with spatially aligned events and RGB frames. Extensive experiments show that our method significantly surpasses the prior-arts and achieves VSR with random scales, e.g., 6.5. Code and dataset are available at https: //vlis2022.github.io/cvpr23/egvsr.

Xu Zheng, Yuanhuiyi Lyu, Jiazhou Zhou et al.

Fusing an arbitrary number of modalities is vital for achieving robust multi-modal fusion of semantic segmentation yet remains less explored to date. Recent endeavors regard RGB modality as the center and the others as the auxiliary, yielding an asymmetric architecture with two branches. However, the RGB modality may struggle in certain circumstances, e.g., nighttime, while others, e.g., event data, own their merits; thus, it is imperative for the fusion model to discern robust and fragile modalities, and incorporate the most robust and fragile ones to learn a resilient multi-modal framework. To this end, we propose a novel method, named MAGIC, that can be flexibly paired with various backbones, ranging from compact to high-performance models. Our method comprises two key plug-and-play modules. Firstly, we introduce a multi-modal aggregation module to efficiently process features from multi-modal batches and extract complementary scene information. On top, a unified arbitrary-modal selection module is proposed to utilize the aggregated features as the benchmark to rank the multi-modal features based on the similarity scores. This way, our method can eliminate the dependence on RGB modality and better overcome sensor failures while ensuring the segmentation performance. Under the commonly considered multi-modal setting, our method achieves state-of-the-art performance while reducing the model parameters by 60%. Moreover, our method is superior in the novel modality-agnostic setting, where it outperforms prior arts by a large margin of +19.41% mIoU

Weiming Zhang, Yexin Liu, Xu Zheng et al.

This paper presents GoodSAM++, a novel framework utilizing the powerful zero-shot instance segmentation capability of SAM (i.e., teacher) to learn a compact panoramic semantic segmentation model, i.e., student, without requiring any labeled data. GoodSAM++ addresses two critical challenges: 1) SAM's inability to provide semantic labels and inherent distortion problems of panoramic images; 2) the significant capacity disparity between SAM and the student. The `out-of-the-box' insight of GoodSAM++ is to introduce a teacher assistant (TA) to provide semantic information for SAM, integrated with SAM to obtain reliable pseudo semantic maps to bridge both domain and capacity gaps. To make this possible, we first propose a Distortion-Aware Rectification (DARv2) module to address the domain gap. It effectively mitigates the object deformation and distortion problem in panoramic images to obtain pseudo semantic maps. We then introduce a Multi-level Knowledge Adaptation (MKA) module to efficiently transfer the semantic information from the TA and pseudo semantic maps to our compact student model, addressing the significant capacity gap. We conduct extensive experiments on both outdoor and indoor benchmark datasets, showing that our GoodSAM++ achieves a remarkable performance improvement over the state-of-the-art (SOTA) domain adaptation methods. Moreover, diverse open-world scenarios demonstrate the generalization capacity of our GoodSAM++. Last but not least, our most lightweight student model achieves comparable performance to the SOTA models with only 3.7 million parameters.

Haotian Bai, Yiqi Lin, Yize Chen et al.

The explicit neural radiance field (NeRF) has gained considerable interest for its efficient training and fast inference capabilities, making it a promising direction such as virtual reality and gaming. In particular, PlenOctree (POT)[1], an explicit hierarchical multi-scale octree representation, has emerged as a structural and influential framework. However, POT's fixed structure for direct optimization is sub-optimal as the scene complexity evolves continuously with updates to cached color and density, necessitating refining the sampling distribution to capture signal complexity accordingly. To address this issue, we propose the dynamic PlenOctree DOT, which adaptively refines the sample distribution to adjust to changing scene complexity. Specifically, DOT proposes a concise yet novel hierarchical feature fusion strategy during the iterative rendering process. Firstly, it identifies the regions of interest through training signals to ensure adaptive and efficient refinement. Next, rather than directly filtering out valueless nodes, DOT introduces the sampling and pruning operations for octrees to aggregate features, enabling rapid parameter learning. Compared with POT, our DOT outperforms it by enhancing visual quality, reducing over $55.15$/$68.84\%$ parameters, and providing 1.7/1.9 times FPS for NeRF-synthetic and Tanks $\&$ Temples, respectively. Project homepage:https://vlislab22.github.io/DOT. [1] Yu, Alex, et al. "Plenoctrees for real-time rendering of neural radiance fields." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.

Yiqi Lin, Huabin Zheng, Huaping Zhong et al.

Recently, the self-supervised pre-training paradigm has shown great potential in leveraging large-scale unlabeled data to improve downstream task performance. However, increasing the scale of unlabeled pre-training data in real-world scenarios requires prohibitive computational costs and faces the challenge of uncurated samples. To address these issues, we build a task-specific self-supervised pre-training framework from a data selection perspective based on a simple hypothesis that pre-training on the unlabeled samples with similar distribution to the target task can bring substantial performance gains. Buttressed by the hypothesis, we propose the first yet novel framework for Scalable and Efficient visual Pre-Training (SEPT) by introducing a retrieval pipeline for data selection. SEPT first leverage a self-supervised pre-trained model to extract the features of the entire unlabeled dataset for retrieval pipeline initialization. Then, for a specific target task, SEPT retrievals the most similar samples from the unlabeled dataset based on feature similarity for each target instance for pre-training. Finally, SEPT pre-trains the target model with the selected unlabeled samples in a self-supervised manner for target data finetuning. By decoupling the scale of pre-training and available upstream data for a target task, SEPT achieves high scalability of the upstream dataset and high efficiency of pre-training, resulting in high model architecture flexibility. Results on various downstream tasks demonstrate that SEPT can achieve competitive or even better performance compared with ImageNet pre-training while reducing the size of training samples by one magnitude without resorting to any extra annotations.

Xu Zheng, Lin Wang

In this paper, we address the challenging problem of cross-modal (image-to-events) adaptation for event-based recognition without accessing any labeled source image data. This task is arduous due to the substantial modality gap between images and events. With only a pre-trained source model available, the key challenge lies in extracting knowledge from this model and effectively transferring knowledge to the event-based domain. Inspired by the natural ability of language to convey semantics across different modalities, we propose EventDance++, a novel framework that tackles this unsupervised source-free cross-modal adaptation problem from a language-guided perspective. We introduce a language-guided reconstruction-based modality bridging (L-RMB) module, which reconstructs intensity frames from events in a self-supervised manner. Importantly, it leverages a vision-language model to provide further supervision, enriching the surrogate images and enhancing modality bridging. This enables the creation of surrogate images to extract knowledge (i.e., labels) from the source model. On top, we propose a multi-representation knowledge adaptation (MKA) module to transfer knowledge to target models, utilizing multiple event representations to capture the spatiotemporal characteristics of events fully. The L-RMB and MKA modules are jointly optimized to achieve optimal performance in bridging the modality gap. Experiments on three benchmark datasets demonstrate that EventDance++ performs on par with methods that utilize source data, validating the effectiveness of our language-guided approach in event-based recognition.

Tianbo Pan, Zidong Cao, Lin Wang

Monocular depth estimation is a crucial task to measure distance relative to a camera, which is important for applications, such as robot navigation and self-driving. Traditional frame-based methods suffer from performance drops due to the limited dynamic range and motion blur. Therefore, recent works leverage novel event cameras to complement or guide the frame modality via frame-event feature fusion. However, event streams exhibit spatial sparsity, leaving some areas unperceived, especially in regions with marginal light changes. Therefore, direct fusion methods, e.g., RAMNet, often ignore the contribution of the most confident regions of each modality. This leads to structural ambiguity in the modality fusion process, thus degrading the depth estimation performance. In this paper, we propose a novel Spatial Reliability-oriented Fusion Network (SRFNet), that can estimate depth with fine-grained structure at both daytime and nighttime. Our method consists of two key technical components. Firstly, we propose an attention-based interactive fusion (AIF) module that applies spatial priors of events and frames as the initial masks and learns the consensus regions to guide the inter-modal feature fusion. The fused feature are then fed back to enhance the frame and event feature learning. Meanwhile, it utilizes an output head to generate a fused mask, which is iteratively updated for learning consensual spatial priors. Secondly, we propose the Reliability-oriented Depth Refinement (RDR) module to estimate dense depth with the fine-grained structure based on the fused features and masks. We evaluate the effectiveness of our method on the synthetic and real-world datasets, which shows that, even without pretraining, our method outperforms the prior methods, e.g., RAMNet, especially in night scenes. Our project homepage: https://vlislab22.github.io/SRFNet.

Lutao Jiang, Hangyu Li, Lin Wang

Text-to-3D content creation has recently received much attention, especially with the prevalence of 3D Gaussians Splatting. In general, GS-based methods comprise two key stages: initialization and rendering optimization. To achieve initialization, existing works directly apply random sphere initialization or 3D diffusion models, e.g., Point-E, to derive the initial shapes. However, such strategies suffer from two critical yet challenging problems: 1) the final shapes are still similar to the initial ones even after training; 2) shapes can be produced only from simple texts, e.g., "a dog", not for lexically richer texts, e.g., "a dog is sitting on the top of the airplane". To address these problems, this paper proposes a novel general framework to boost the 3D GS Initialization for text-to-3D generation upon the lexical richness. Our key idea is to aggregate 3D Gaussians into spatially uniform voxels to represent complex shapes while enabling the spatial interaction among the 3D Gaussians and semantic interaction between Gaussians and texts. Specifically, we first construct a voxelized representation, where each voxel holds a 3D Gaussian with its position, scale, and rotation fixed while setting opacity as the sole factor to determine a position's occupancy. We then design an initialization network mainly consisting of two novel components: 1) Global Information Perception (GIP) block and 2) Gaussians-Text Fusion (GTF) block. Such a design enables each 3D Gaussian to assimilate the spatial information from other areas and semantic information from texts. Extensive experiments show the superiority of our framework of high-quality 3D GS initialization against the existing methods, e.g., Shap-E, by taking lexically simple, medium, and hard texts. Also, our framework can be seamlessly plugged into SoTA training frameworks, e.g., LucidDreamer, for semantically consistent text-to-3D generation.

Tongyan Hua, Lin Wang

Implicit neural representation (INR), in combination with geometric rendering, has recently been employed in real-time dense RGB-D SLAM. Despite active research endeavors being made, there lacks a unified protocol for fair evaluation, impeding the evolution of this area. In this work, we establish, to our knowledge, the first open-source benchmark framework to evaluate the performance of a wide spectrum of commonly used INRs and rendering functions for mapping and localization. The goal of our benchmark is to 1) gain an intuition of how different INRs and rendering functions impact mapping and localization and 2) establish a unified evaluation protocol w.r.t. the design choices that may impact the mapping and localization. With the framework, we conduct a large suite of experiments, offering various insights in choosing the INRs and geometric rendering functions: for example, the dense feature grid outperforms other INRs (e.g. tri-plane and hash grid), even when geometric and color features are jointly encoded for memory efficiency. To extend the findings into the practical scenario, a hybrid encoding strategy is proposed to bring the best of the accuracy and completion from the grid-based and decomposition-based INRs. We further propose explicit hybrid encoding for high-fidelity dense grid mapping to comply with the RGB-D SLAM system that puts the premise on robustness and computation efficiency.

Hao Ai, Lin Wang

360 cameras capture the entire surrounding environment with a large FoV, exhibiting comprehensive visual information to directly infer the 3D structures, e.g., depth and surface normal, and semantic information simultaneously. Existing works predominantly specialize in a single task, leaving multi-task learning of 3D geometry and semantics largely unexplored. Achieving such an objective is, however, challenging due to: 1) inherent spherical distortion of planar equirectangular projection (ERP) and insufficient global perception induced by 360 image's ultra-wide FoV; 2) non-trivial progress in effectively merging geometry and semantics among different tasks to achieve mutual benefits. In this paper, we propose a novel end-to-end multi-task learning framework, named Elite360M, capable of inferring 3D structures via depth and surface normal estimation, and semantics via semantic segmentation simultaneously. Our key idea is to build a representation with strong global perception and less distortion while exploring the inter- and cross-task relationships between geometry and semantics. We incorporate the distortion-free and spatially continuous icosahedron projection (ICOSAP) points and combine them with ERP to enhance global perception. With a negligible cost, a Bi-projection Bi-attention Fusion module is thus designed to capture the semantic- and distance-aware dependencies between each pixel of the region-aware ERP feature and the ICOSAP point feature set. Moreover, we propose a novel Cross-task Collaboration module to explicitly extract task-specific geometric and semantic information from the learned representation to achieve preliminary predictions. It then integrates the spatial contextual information among tasks to realize cross-task fusion. Extensive experiments demonstrate the effectiveness and efficacy of Elite360M.

Jinjing Zhu, Yucheng Chen, Lin Wang

Unsupervised domain adaption (UDA) has emerged as a popular solution to tackle the divergence between the labeled source and unlabeled target domains. Recently, some research efforts have been made to leverage large vision-language models, such as CLIP, and then fine-tune or learn prompts from them for addressing the challenging UDA task. In this work, we shift the gear to a new direction by directly leveraging CLIP to measure the domain divergence and propose a novel language-guided approach for UDA, dubbed as CLIP-Div. Our key idea is to harness CLIP to 1) measure the domain divergence via the acquired domain-agnostic distribution and 2) calibrate the target pseudo labels with language guidance, to effectively reduce the domain gap and improve the UDA model's generalization capability. Specifically, our major technical contribution lies in the proposed two novel language-guided domain divergence measurement losses: absolute divergence and relative divergence. These loss terms furnish precise guidelines for aligning the distributions of the source and target domains with the domain-agnostic distribution derived from CLIP. Additionally, we propose a language-guided pseudo-labeling strategy for calibrating the target pseudo labels. Buttressed by it, we show that a further implementation for self-training can enhance the UDA model's generalization capability on the target domain. CLIP-Div surpasses state-of-the-art CNN-based methods by a substantial margin, achieving a performance boost of +10.3% on Office-Home, +1.5% on Office-31, +0.2% on VisDA-2017, and +24.3% on DomainNet, respectively.

Haoran Li, Haolin Shi, Wenli Zhang et al.

Text-to-3D scene generation holds immense potential for the gaming, film, and architecture sectors. Despite significant progress, existing methods struggle with maintaining high quality, consistency, and editing flexibility. In this paper, we propose DreamScene, a 3D Gaussian-based novel text-to-3D scene generation framework, to tackle the aforementioned three challenges mainly via two strategies. First, DreamScene employs Formation Pattern Sampling (FPS), a multi-timestep sampling strategy guided by the formation patterns of 3D objects, to form fast, semantically rich, and high-quality representations. FPS uses 3D Gaussian filtering for optimization stability, and leverages reconstruction techniques to generate plausible textures. Second, DreamScene employs a progressive three-stage camera sampling strategy, specifically designed for both indoor and outdoor settings, to effectively ensure object-environment integration and scene-wide 3D consistency. Last, DreamScene enhances scene editing flexibility by integrating objects and environments, enabling targeted adjustments. Extensive experiments validate DreamScene's superiority over current state-of-the-art techniques, heralding its wide-ranging potential for diverse applications. Code and demos will be released at https://dreamscene-project.github.io .

Jingyi Pan, Zipeng Wang, Lin Wang

3D semantic occupancy prediction is a pivotal task in the field of autonomous driving. Recent approaches have made great advances in 3D semantic occupancy predictions on a single modality. However, multi-modal semantic occupancy prediction approaches have encountered difficulties in dealing with the modality heterogeneity, modality misalignment, and insufficient modality interactions that arise during the fusion of different modalities data, which may result in the loss of important geometric and semantic information. This letter presents a novel multi-modal, i.e., LiDAR-camera 3D semantic occupancy prediction framework, dubbed Co-Occ, which couples explicit LiDAR-camera feature fusion with implicit volume rendering regularization. The key insight is that volume rendering in the feature space can proficiently bridge the gap between 3D LiDAR sweeps and 2D images while serving as a physical regularization to enhance LiDAR-camera fused volumetric representation. Specifically, we first propose a Geometric- and Semantic-aware Fusion (GSFusion) module to explicitly enhance LiDAR features by incorporating neighboring camera features through a K-nearest neighbors (KNN) search. Then, we employ volume rendering to project the fused feature back to the image planes for reconstructing color and depth maps. These maps are then supervised by input images from the camera and depth estimations derived from LiDAR, respectively. Extensive experiments on the popular nuScenes and SemanticKITTI benchmarks verify the effectiveness of our Co-Occ for 3D semantic occupancy prediction. The project page is available at https://rorisis.github.io/Co-Occ_project-page/.

Xu Zheng, Lin Wang

In this paper, we make the first attempt at achieving the cross-modal (i.e., image-to-events) adaptation for event-based object recognition without accessing any labeled source image data owning to privacy and commercial issues. Tackling this novel problem is non-trivial due to the novelty of event cameras and the distinct modality gap between images and events. In particular, as only the source model is available, a hurdle is how to extract the knowledge from the source model by only using the unlabeled target event data while achieving knowledge transfer. To this end, we propose a novel framework, dubbed EventDance for this unsupervised source-free cross-modal adaptation problem. Importantly, inspired by event-to-video reconstruction methods, we propose a reconstruction-based modality bridging (RMB) module, which reconstructs intensity frames from events in a self-supervised manner. This makes it possible to build up the surrogate images to extract the knowledge (i.e., labels) from the source model. We then propose a multi-representation knowledge adaptation (MKA) module that transfers the knowledge to target models learning events with multiple representation types for fully exploring the spatiotemporal information of events. The two modules connecting the source and target models are mutually updated so as to achieve the best performance. Experiments on three benchmark datasets with two adaption settings show that EventDance is on par with prior methods utilizing the source data.

Xu Zheng, Pengyuan Zhou, Athanasios V. Vasilakos et al.

In this paper, we address the challenging source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation, given only a pinhole image pre-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is non-trivial due to three critical challenges: 1) semantic mismatches from the distinct Field-of-View (FoV) between domains, 2) style discrepancies inherent in the UDA problem, and 3) inevitable distortion of the panoramic images. To tackle these problems, we propose 360SFUDA++ that effectively extracts knowledge from the source pinhole model with only unlabeled panoramic images and transfers the reliable knowledge to the target panoramic domain. Specifically, we first utilize Tangent Projection (TP) as it has less distortion and meanwhile slits the equirectangular projection (ERP) to patches with fixed FoV projection (FFP) to mimic the pinhole images. Both projections are shown effective in extracting knowledge from the source model. However, as the distinct projections make it less possible to directly transfer knowledge between domains, we then propose Reliable Panoramic Prototype Adaptation Module (RP2AM) to transfer knowledge at both prediction and prototype levels. RP$^2$AM selects the confident knowledge and integrates panoramic prototypes for reliable knowledge adaptation. Moreover, we introduce Cross-projection Dual Attention Module (CDAM), which better aligns the spatial and channel characteristics across projections at the feature level between domains. Both knowledge extraction and transfer processes are synchronously updated to reach the best performance. Extensive experiments on the synthetic and real-world benchmarks, including outdoor and indoor scenarios, demonstrate that our 360SFUDA++ achieves significantly better performance than prior SFUDA methods.

Hao Ai, Lin Wang

360 depth estimation has recently received great attention for 3D reconstruction owing to its omnidirectional field of view (FoV). Recent approaches are predominantly focused on cross-projection fusion with geometry-based re-projection: they fuse 360 images with equirectangular projection (ERP) and another projection type, e.g., cubemap projection to estimate depth with the ERP format. However, these methods suffer from 1) limited local receptive fields, making it hardly possible to capture large FoV scenes, and 2) prohibitive computational cost, caused by the complex cross-projection fusion module design. In this paper, we propose Elite360D, a novel framework that inputs the ERP image and icosahedron projection (ICOSAP) point set, which is undistorted and spatially continuous. Elite360D is superior in its capacity in learning a representation from a local-with-global perspective. With a flexible ERP image encoder, it includes an ICOSAP point encoder, and a Bi-projection Bi-attention Fusion (B2F) module (totally ~1M parameters). Specifically, the ERP image encoder can take various perspective image-trained backbones (e.g., ResNet, Transformer) to extract local features. The point encoder extracts the global features from the ICOSAP. Then, the B2F module captures the semantic- and distance-aware dependencies between each pixel of the ERP feature and the entire ICOSAP feature set. Without specific backbone design and obvious computational cost increase, Elite360D outperforms the prior arts on several benchmark datasets.

Weiming Zhang, Yexin Liu, Xu Zheng et al.

This paper tackles a novel yet challenging problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) -- which reveals impressive zero-shot instance segmentation capacity -- to learn a compact panoramic semantic segmentation model, i.e., student, without requiring any labeled data. This poses considerable challenges due to SAM's inability to provide semantic labels and the large capacity gap between SAM and the student. To this end, we propose a novel framework, called GoodSAM, that introduces a teacher assistant (TA) to provide semantic information, integrated with SAM to generate ensemble logits to achieve knowledge transfer. Specifically, we propose a Distortion-Aware Rectification (DAR) module that first addresses the distortion problem of panoramic images by imposing prediction-level consistency and boundary enhancement. This subtly enhances TA's prediction capacity on panoramic images. DAR then incorporates a cross-task complementary fusion block to adaptively merge the predictions of SAM and TA to obtain more reliable ensemble logits. Moreover, we introduce a Multi-level Knowledge Adaptation (MKA) module to efficiently transfer the multi-level feature knowledge from TA and ensemble logits to learn a compact student model. Extensive experiments on two benchmarks show that our GoodSAM achieves a remarkable +3.75\% mIoU improvement over the state-of-the-art (SOTA) domain adaptation methods. Also, our most lightweight model achieves comparable performance to the SOTA methods with only 3.7M parameters.

Kun Lan, Haoran Li, Haolin Shi et al.

Recently, 3D Gaussian, as an explicit 3D representation method, has demonstrated strong competitiveness over NeRF (Neural Radiance Fields) in terms of expressing complex scenes and training duration. These advantages signal a wide range of applications for 3D Gaussians in 3D understanding and editing. Meanwhile, the segmentation of 3D Gaussians is still in its infancy. The existing segmentation methods are not only cumbersome but also incapable of segmenting multiple objects simultaneously in a short amount of time. In response, this paper introduces a 3D Gaussian segmentation method implemented with 2D segmentation as supervision. This approach uses input 2D segmentation maps to guide the learning of the added 3D Gaussian semantic information, while nearest neighbor clustering and statistical filtering refine the segmentation results. Experiments show that our concise method can achieve comparable performances on mIOU and mAcc for multi-object segmentation as previous single-object segmentation methods.

Yuanhuiyi Lyu, Xu Zheng, Lin Wang

The multifaceted nature of human perception and comprehension indicates that, when we think, our body can naturally take any combination of senses, a.k.a., modalities and form a beautiful picture in our brain. For example, when we see a cattery and simultaneously perceive the cat's purring sound, our brain can construct a picture of a cat in the cattery. Intuitively, generative AI models should hold the versatility of humans and be capable of generating images from any combination of modalities efficiently and collaboratively. This paper presents ImgAny, a novel end-to-end multi-modal generative model that can mimic human reasoning and generate high-quality images. Our method serves as the first attempt in its capacity of efficiently and flexibly taking any combination of seven modalities, ranging from language, audio to vision modalities, including image, point cloud, thermal, depth, and event data. Our key idea is inspired by human-level cognitive processes and involves the integration and harmonization of multiple input modalities at both the entity and attribute levels without specific tuning across modalities. Accordingly, our method brings two novel training-free technical branches: 1) Entity Fusion Branch ensures the coherence between inputs and outputs. It extracts entity features from the multi-modal representations powered by our specially constructed entity knowledge graph; 2) Attribute Fusion Branch adeptly preserves and processes the attributes. It efficiently amalgamates distinct attributes from diverse input modalities via our proposed attribute knowledge graph. Lastly, the entity and attribute features are adaptively fused as the conditional inputs to the pre-trained Stable Diffusion model for image generation. Extensive experiments under diverse modality combinations demonstrate its exceptional capability for visual content creation.

Zixiang Wei, Yiting Wang, Lichao Sun et al.

Low-light images often suffer from limited visibility and multiple types of degradation, rendering low-light image enhancement (LIE) a non-trivial task. Some endeavors have been recently made to enhance low-light images using convolutional neural networks (CNNs). However, they have low efficiency in learning the structural information and diverse illumination levels at the local regions of an image. Consequently, the enhanced results are affected by unexpected artifacts, such as unbalanced exposure, blur, and color bias. To this end, this paper proposes a novel framework, called ClassLIE, that combines the potential of CNNs and transformers. It classifies and adaptively learns the structural and illumination information from the low-light images in a holistic and regional manner, thus showing better enhancement performance. Our framework first employs a structure and illumination classification (SIC) module to learn the degradation information adaptively. In SIC, we decompose an input image into an illumination map and a reflectance map. A class prediction block is then designed to classify the degradation information by calculating the structure similarity scores on the reflectance map and mean square error on the illumination map. As such, each input image can be divided into patches with three enhancement difficulty levels. Then, a feature learning and fusion (FLF) module is proposed to adaptively learn the feature information with CNNs for different enhancement difficulty levels while learning the long-range dependencies for the patches in a holistic manner. Experiments on five benchmark datasets consistently show our ClassLIE achieves new state-of-the-art performance, with 25.74 PSNR and 0.92 SSIM on the LOL dataset.

Tongyan Hua, Haotian Bai, Zidong Cao et al.

In this paper, we introduce Hi-Map, a novel monocular dense mapping approach based on Neural Radiance Field (NeRF). Hi-Map is exceptional in its capacity to achieve efficient and high-fidelity mapping using only posed RGB inputs. Our method eliminates the need for external depth priors derived from e.g., a depth estimation model. Our key idea is to represent the scene as a hierarchical feature grid that encodes the radiance and then factorizes it into feature planes and vectors. As such, the scene representation becomes simpler and more generalizable for fast and smooth convergence on new observations. This allows for efficient computation while alleviating noise patterns by reducing the complexity of the scene representation. Buttressed by the hierarchical factorized representation, we leverage the Sign Distance Field (SDF) as a proxy of rendering for inferring the volume density, demonstrating high mapping fidelity. Moreover, we introduce a dual-path encoding strategy to strengthen the photometric cues and further boost the mapping quality, especially for the distant and textureless regions. Extensive experiments demonstrate our method's superiority in geometric and textural accuracy over the state-of-the-art NeRF-based monocular mapping methods.

Jian Liu, Xiongtao Shi, Thai Duy Nguyen et al.

The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments. Despite advancements in pattern recognition and symbolic reasoning, current AI systems, such as large language models, remain disembodied, unable to physically engage with the world. This limitation has driven the rise of embodied AI, where autonomous agents, such as humanoid robots, must navigate and manipulate unstructured environments with human-like adaptability. At the core of this challenge lies the concept of Neural Brain, a central intelligence system designed to drive embodied agents with human-like adaptability. A Neural Brain must seamlessly integrate multimodal sensing and perception with cognitive capabilities. Achieving this also requires an adaptive memory system and energy-efficient hardware-software co-design, enabling real-time action in dynamic environments. This paper introduces a unified framework for the Neural Brain of embodied agents, addressing two fundamental challenges: (1) defining the core components of Neural Brain and (2) bridging the gap between static AI models and the dynamic adaptability required for real-world deployment. To this end, we propose a biologically inspired architecture that integrates multimodal active sensing, perception-cognition-action function, neuroplasticity-based memory storage and updating, and neuromorphic hardware/software optimization. Furthermore, we also review the latest research on embodied agents across these four aspects and analyze the gap between current AI systems and human intelligence. By synthesizing insights from neuroscience, we outline a roadmap towards the development of generalizable, autonomous agents capable of human-level intelligence in real-world scenarios.

Jinjing Zhu, Yucheng Chen, Lin Wang

Source-free cross-modal knowledge transfer is a crucial yet challenging task, which aims to transfer knowledge from one source modality (e.g., RGB) to the target modality (e.g., depth or infrared) with no access to the task-relevant (TR) source data due to memory and privacy concerns. A recent attempt leverages the paired task-irrelevant (TI) data and directly matches the features from them to eliminate the modality gap. However, it ignores a pivotal clue that the paired TI data could be utilized to effectively estimate the source data distribution and better facilitate knowledge transfer to the target modality. To this end, we propose a novel yet concise framework to unlock the potential of paired TI data for enhancing source-free cross-modal knowledge transfer. Our work is buttressed by two key technical components. Firstly, to better estimate the source data distribution, we introduce a Task-irrelevant data-Guided Modality Bridging (TGMB) module. It translates the target modality data (e.g., infrared) into the source-like RGB images based on paired TI data and the guidance of the available source model to alleviate two key gaps: 1) inter-modality gap between the paired TI data; 2) intra-modality gap between TI and TR target data. We then propose a Task-irrelevant data-Guided Knowledge Transfer (TGKT) module that transfers knowledge from the source model to the target model by leveraging the paired TI data. Notably, due to the unavailability of labels for the TR target data and its less reliable prediction from the source model, our TGKT model incorporates a self-supervised pseudo-labeling approach to enable the target model to learn from its predictions. Extensive experiments show that our method achieves state-of-the-art performance on three datasets (RGB-to-depth and RGB-to-infrared).

Jinjing Zhu, Zhedong Hu, Tae-Kyun Kim et al.

Recent endeavors have been made to leverage self-supervised depth estimation as guidance in unsupervised domain adaptation (UDA) for semantic segmentation. Prior arts, however, overlook the discrepancy between semantic and depth features, as well as the reliability of feature fusion, thus leading to suboptimal segmentation performance. To address this issue, we propose a novel UDA framework called SMART (croSs doMain semAntic segmentation based on eneRgy esTimation) that utilizes Energy-Based Models (EBMs) to obtain task-adaptive features and achieve reliable feature fusion for semantic segmentation with self-supervised depth estimates. Our framework incorporates two novel components: energy-based feature fusion (EB2F) and energy-based reliable fusion Assessment (RFA) modules. The EB2F module produces task-adaptive semantic and depth features by explicitly measuring and reducing their discrepancy using Hopfield energy for better feature fusion. The RFA module evaluates the reliability of the feature fusion using an energy score to improve the effectiveness of depth guidance. Extensive experiments on two datasets demonstrate that our method achieves significant performance gains over prior works, validating the effectiveness of our energy-based learning approach.

L'ea Dubois, Klaus Schmidt, Chengyu Wang et al.

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To bridge this cognitive gap, we propose a novel framework that synergistically fuses a powerful Vision Foundation Model (VFM) for deep visual perception with a Large Language Model (LLM) serving as a knowledge-driven reasoning core. Our key technical innovation is a sophisticated fusion module, inspired by the Q-Former architecture, which distills complex spatiotemporal and object-centric visual features into a concise, language-aligned representation. This enables the LLM to effectively ground its inferential processes in direct visual evidence. The model is trained via a two-stage strategy, beginning with large-scale alignment pre-training on video-text data, followed by targeted instruction fine-tuning on a curated dataset designed to elicit advanced reasoning and prediction skills. Extensive experiments demonstrate that our model achieves state-of-the-art performance on multiple challenging benchmarks. Notably, it exhibits remarkable zero-shot generalization to unseen reasoning tasks, and our in-depth ablation studies validate the critical contribution of each architectural component. This work pushes the boundary of machine perception from simple recognition towards genuine cognitive understanding, paving the way for more intelligent and capable AI systems in robotics, human-computer interaction, and beyond.

Yexin Liu, Weiming Zhang, Athanasios V. Vasilakos et al.

Unsupervised visible-infrared person re-identification (UVI-ReID) has recently gained great attention due to its potential for enhancing human detection in diverse environments without labeling. Previous methods utilize intra-modality clustering and cross-modality feature matching to achieve UVI-ReID. However, there exist two challenges: 1) noisy pseudo labels might be generated in the clustering process, and 2) the cross-modality feature alignment via matching the marginal distribution of visible and infrared modalities may misalign the different identities from two modalities. In this paper, we first conduct a theoretic analysis where an interpretable generalization upper bound is introduced. Based on the analysis, we then propose a novel unsupervised cross-modality person re-identification framework (PRAISE). Specifically, to address the first challenge, we propose a pseudo-label correction strategy that utilizes a Beta Mixture Model to predict the probability of mis-clustering based network's memory effect and rectifies the correspondence by adding a perceptual term to contrastive learning. Next, we introduce a modality-level alignment strategy that generates paired visible-infrared latent features and reduces the modality gap by aligning the labeling function of visible and infrared features to learn identity discriminative and modality-invariant features. Experimental results on two benchmark datasets demonstrate that our method achieves state-of-the-art performance than the unsupervised visible-ReID methods.

Yang Song, Lin Wang

3D object detection is an important task that has been widely applied in autonomous driving. To perform this task, a new trend is to fuse multi-modal inputs, i.e., LiDAR and camera. Under such a trend, recent methods fuse these two modalities by unifying them in the same 3D space. However, during direct fusion in a unified space, the drawbacks of both modalities (LiDAR features struggle with detailed semantic information and the camera lacks accurate 3D spatial information) are also preserved, diluting semantic and spatial awareness of the final unified representation. To address the issue, this letter proposes a novel bidirectional complementary LiDAR-camera fusion framework, called BiCo-Fusion that can achieve robust semantic- and spatial-aware 3D object detection. The key insight is to fuse LiDAR and camera features in a bidirectional complementary way to enhance the semantic awareness of the LiDAR and the 3D spatial awareness of the camera. The enhanced features from both modalities are then adaptively fused to build a semantic- and spatial-aware unified representation. Specifically, we introduce Pre-Fusion consisting of a Voxel Enhancement Module (VEM) to enhance the semantic awareness of voxel features from 2D camera features and Image Enhancement Module (IEM) to enhance the 3D spatial awareness of camera features from 3D voxel features. We then introduce Unified Fusion (U-Fusion) to adaptively fuse the enhanced features from the last stage to build a unified representation. Extensive experiments demonstrate the superiority of our BiCo-Fusion against the prior arts. Project page: https://t-ys.github.io/BiCo-Fusion/.

Xu Zheng, Pengyuan Zhou, Athanasios V. Vasilakos et al.

This paper addresses an interesting yet challenging problem -- source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation -- given only a pinhole image-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is nontrivial due to the semantic mismatches, style discrepancies, and inevitable distortion of panoramic images. To this end, we propose a novel method that utilizes Tangent Projection (TP) as it has less distortion and meanwhile slits the equirectangular projection (ERP) with a fixed FoV to mimic the pinhole images. Both projections are shown effective in extracting knowledge from the source model. However, the distinct projection discrepancies between source and target domains impede the direct knowledge transfer; thus, we propose a panoramic prototype adaptation module (PPAM) to integrate panoramic prototypes from the extracted knowledge for adaptation. We then impose the loss constraints on both predictions and prototypes and propose a cross-dual attention module (CDAM) at the feature level to better align the spatial and channel characteristics across the domains and projections. Both knowledge extraction and transfer processes are synchronously updated to reach the best performance. Extensive experiments on the synthetic and real-world benchmarks, including outdoor and indoor scenarios, demonstrate that our method achieves significantly better performance than prior SFUDA methods for pinhole-to-panoramic adaptation.

Hao Ai, Zidong Cao, Haonan Lu et al.

360 images, with a field-of-view (FoV) of 180x360, provide immersive and realistic environments for emerging virtual reality (VR) applications, such as virtual tourism, where users desire to create diverse panoramic scenes from a narrow FoV photo they take from a viewpoint via portable devices. It thus brings us to a technical challenge: `How to allow the users to freely create diverse and immersive virtual scenes from a narrow FoV image with a specified viewport?' To this end, we propose a transformer-based 360 image outpainting framework called Dream360, which can generate diverse, high-fidelity, and high-resolution panoramas from user-selected viewports, considering the spherical properties of 360 images. Compared with existing methods, e.g., [3], which primarily focus on inputs with rectangular masks and central locations while overlooking the spherical property of 360 images, our Dream360 offers higher outpainting flexibility and fidelity based on the spherical representation. Dream360 comprises two key learning stages: (I) codebook-based panorama outpainting via Spherical-VQGAN (S-VQGAN), and (II) frequency-aware refinement with a novel frequency-aware consistency loss. Specifically, S-VQGAN learns a sphere-specific codebook from spherical harmonic (SH) values, providing a better representation of spherical data distribution for scene modeling. The frequency-aware refinement matches the resolution and further improves the semantic consistency and visual fidelity of the generated results. Our Dream360 achieves significantly lower Frechet Inception Distance (FID) scores and better visual fidelity than existing methods. We also conducted a user study involving 15 participants to interactively evaluate the quality of the generated results in VR, demonstrating the flexibility and superiority of our Dream360 framework.

Yiqi Lin, Hao Wu, Ruichen Wang et al.

Generating and editing a 3D scene guided by natural language poses a challenge, primarily due to the complexity of specifying the positional relations and volumetric changes within the 3D space. Recent advancements in Large Language Models (LLMs) have demonstrated impressive reasoning, conversational, and zero-shot generation abilities across various domains. Surprisingly, these models also show great potential in realizing and interpreting the 3D space. In light of this, we propose a novel language-guided interactive 3D generation system, dubbed LI3D, that integrates LLMs as a 3D layout interpreter into the off-the-shelf layout-to-3D generative models, allowing users to flexibly and interactively generate visual content. Specifically, we design a versatile layout structure base on the bounding boxes and semantics to prompt the LLMs to model the spatial generation and reasoning from language. Our system also incorporates LLaVA, a large language and vision assistant, to provide generative feedback from the visual aspect for improving the visual quality of generated content. We validate the effectiveness of LI3D, primarily in 3D generation and editing through multi-round interactions, which can be flexibly extended to 2D generation and editing. Various experiments demonstrate the potential benefits of incorporating LLMs in generative AI for applications, e.g., metaverse. Moreover, we benchmark the layout reasoning performance of LLMs with neural visual artist tasks, revealing their emergent ability in the spatial layout domain.

Taewoo Kim, Jeongmin Lee, Lin Wang et al.

Motion deblurring is a highly ill-posed problem due to the loss of motion information in the blur degradation process. Since event cameras can capture apparent motion with a high temporal resolution, several attempts have explored the potential of events for guiding deblurring. These methods generally assume that the exposure time is the same as the reciprocal of the video frame rate. However, this is not true in real situations, and the exposure time might be unknown and dynamically varies depending on the video shooting environment(e.g., illumination condition). In this paper, we address the event-guided motion deblurring assuming dynamically variable unknown exposure time of the frame-based camera. To this end, we first derive a new formulation for event-guided motion deblurring by considering the exposure and readout time in the video frame acquisition process. We then propose a novel end-to-end learning framework for event-guided motion deblurring. In particular, we design a novel Exposure Time-based Event Selection(ETES) module to selectively use event features by estimating the cross-modal correlation between the features from blurred frames and the events. Moreover, we propose a feature fusion module to fuse the selected features from events and blur frames effectively. We conduct extensive experiments on various datasets and demonstrate that our method achieves state-of-the-art performance.

Youngho Yoon, Inchul Chung, Lin Wang et al.

The 360°imaging has recently gained great attention; however, its angular resolution is relatively lower than that of a narrow field-of-view (FOV) perspective image as it is captured by using fisheye lenses with the same sensor size. Therefore, it is beneficial to super-resolve a 360°image. Some attempts have been made but mostly considered the equirectangular projection (ERP) as one of the way for 360°image representation despite of latitude-dependent distortions. In that case, as the output high-resolution(HR) image is always in the same ERP format as the low-resolution (LR) input, another information loss may occur when transforming the HR image to other projection types. In this paper, we propose SphereSR, a novel framework to generate a continuous spherical image representation from an LR 360°image, aiming at predicting the RGB values at given spherical coordinates for super-resolution with an arbitrary 360°image projection. Specifically, we first propose a feature extraction module that represents the spherical data based on icosahedron and efficiently extracts features on the spherical surface. We then propose a spherical local implicit image function (SLIIF) to predict RGB values at the spherical coordinates. As such, SphereSR flexibly reconstructs an HR image under an arbitrary projection type. Experiments on various benchmark datasets show that our method significantly surpasses existing methods.

Changgyoon Oh, Wonjune Cho, Daehee Park et al.

Providing omnidirectional depth along with RGB information is important for numerous applications, eg, VR/AR. However, as omnidirectional RGB-D data is not always available, synthesizing RGB-D panorama data from limited information of a scene can be useful. Therefore, some prior works tried to synthesize RGB panorama images from perspective RGB images; however, they suffer from limited image quality and can not be directly extended for RGB-D panorama synthesis. In this paper, we study a new problem: RGB-D panorama synthesis under the arbitrary configurations of cameras and depth sensors. Accordingly, we propose a novel bi-modal (RGB-D) panorama synthesis (BIPS) framework. Especially, we focus on indoor environments where the RGB-D panorama can provide a complete 3D model for many applications. We design a generator that fuses the bi-modal information and train it with residual-aided adversarial learning (RDAL). RDAL allows to synthesize realistic indoor layout structures and interiors by jointly inferring RGB panorama, layout depth, and residual depth. In addition, as there is no tailored evaluation metric for RGB-D panorama synthesis, we propose a novel metric to effectively evaluate its perceptual quality. Extensive experiments show that our method synthesizes high-quality indoor RGB-D panoramas and provides realistic 3D indoor models than prior methods. Code will be released upon acceptance.

Lin Wang, Yujeong Chae, Sung-Hoon Yoon et al.

Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A hurdle of training event-based models is the lack of large qualitative labeled data. Prior works learning end-tasks mostly rely on labeled or pseudo-labeled datasets obtained from the active pixel sensor (APS) frames; however, such datasets' quality is far from rivaling those based on the canonical images. In this paper, we propose a novel approach, called \textbf{EvDistill}, to learn a student network on the unlabeled and unpaired event data (target modality) via knowledge distillation (KD) from a teacher network trained with large-scale, labeled image data (source modality). To enable KD across the unpaired modalities, we first propose a bidirectional modality reconstruction (BMR) module to bridge both modalities and simultaneously exploit them to distill knowledge via the crafted pairs, causing no extra computation in the inference. The BMR is improved by the end-tasks and KD losses in an end-to-end manner. Second, we leverage the structural similarities of both modalities and adapt the knowledge by matching their distributions. Moreover, as most prior feature KD methods are uni-modality and less applicable to our problem, we propose to leverage an affinity graph KD loss to boost the distillation. Our extensive experiments on semantic segmentation and object recognition demonstrate that EvDistill achieves significantly better results than the prior works and KD with only events and APS frames.

Lin Wang, Kuk-Jin Yoon

High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision. In recent years, there has been a significant advancement in HDR imaging using deep learning (DL). This study conducts a comprehensive and insightful survey and analysis of recent developments in deep HDR imaging methodologies. We hierarchically and structurally group existing deep HDR imaging methods into five categories based on (1) number/domain of input exposures, (2) number of learning tasks, (3) novel sensor data, (4) novel learning strategies, and (5) applications. Importantly, we provide a constructive discussion on each category regarding its potential and challenges. Moreover, we review some crucial aspects of deep HDR imaging, such as datasets and evaluation metrics. Finally, we highlight some open problems and point out future research directions.