Dingwen Zhang

Ziyang Luo, Nian Liu, Wangbo Zhao et al.

Salient object detection (SOD) and camouflaged object detection (COD) are related yet distinct binary mapping tasks. These tasks involve multiple modalities, sharing commonalities and unique cues. Existing research often employs intricate task-specific specialist models, potentially leading to redundancy and suboptimal results. We introduce VSCode, a generalist model with novel 2D prompt learning, to jointly address four SOD tasks and three COD tasks. We utilize VST as the foundation model and introduce 2D prompts within the encoder-decoder architecture to learn domain and task-specific knowledge on two separate dimensions. A prompt discrimination loss helps disentangle peculiarities to benefit model optimization. VSCode outperforms state-of-the-art methods across six tasks on 26 datasets and exhibits zero-shot generalization to unseen tasks by combining 2D prompts, such as RGB-D COD. Source code has been available at https://github.com/Sssssuperior/VSCode.

Le Yang, Junwei Han, Dingwen Zhang

Online action detection has attracted increasing research interests in recent years. Current works model historical dependencies and anticipate the future to perceive the action evolution within a video segment and improve the detection accuracy. However, the existing paradigm ignores category-level modeling and does not pay sufficient attention to efficiency. Considering a category, its representative frames exhibit various characteristics. Thus, the category-level modeling can provide complimentary guidance to the temporal dependencies modeling. This paper develops an effective exemplar-consultation mechanism that first measures the similarity between a frame and exemplary frames, and then aggregates exemplary features based on the similarity weights. This is also an efficient mechanism, as both similarity measurement and feature aggregation require limited computations. Based on the exemplar-consultation mechanism, the long-term dependencies can be captured by regarding historical frames as exemplars, while the category-level modeling can be achieved by regarding representative frames from a category as exemplars. Due to the complementarity from the category-level modeling, our method employs a lightweight architecture but achieves new high performance on three benchmarks. In addition, using a spatio-temporal network to tackle video frames, our method makes a good trade-off between effectiveness and efficiency. Code is available at https://github.com/VividLe/Online-Action-Detection.

Le Yang, Junwei Han, Tao Zhao et al.

Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective modules to precisely localize action instances based on appearance and motion features. However, by treating these two kinds of features with equal importance, previous works cannot take full advantage of each modality feature, making the learned model still sub-optimal. To tackle this issue, we make an early effort to study temporal action localization from the perspective of multi-modality feature learning, based on the observation that different actions exhibit specific preferences to appearance or motion modality. Specifically, we build a novel structured attention composition module. Unlike conventional attention, the proposed module would not infer frame attention and modality attention independently. Instead, by casting the relationship between the modality attention and the frame attention as an attention assignment process, the structured attention composition module learns to encode the frame-modality structure and uses it to regularize the inferred frame attention and modality attention, respectively, upon the optimal transport theory. The final frame-modality attention is obtained by the composition of the two individual attentions. The proposed structured attention composition module can be deployed as a plug-and-play module into existing action localization frameworks. Extensive experiments on two widely used benchmarks show that the proposed structured attention composition consistently improves four state-of-the-art temporal action localization methods and builds new state-of-the-art performance on THUMOS14. Code is availabel at https://github.com/VividLe/Structured-Attention-Composition.

Chengwei Pan, Gangming Zhao, Junjie Fang et al.

Although deep learning algorithms have been intensively developed for computer-aided tuberculosis diagnosis (CTD), they mainly depend on carefully annotated datasets, leading to much time and resource consumption. Weakly supervised learning (WSL), which leverages coarse-grained labels to accomplish fine-grained tasks, has the potential to solve this problem. In this paper, we first propose a new large-scale tuberculosis (TB) chest X-ray dataset, namely the tuberculosis chest X-ray attribute dataset (TBX-Att), and then establish an attribute-assisted weakly-supervised framework to classify and localize TB by leveraging the attribute information to overcome the insufficiency of supervision in WSL scenarios. Specifically, first, the TBX-Att dataset contains 2000 X-ray images with seven kinds of attributes for TB relational reasoning, which are annotated by experienced radiologists. It also includes the public TBX11K dataset with 11200 X-ray images to facilitate weakly supervised detection. Second, we exploit a multi-scale feature interaction model for TB area classification and detection with attribute relational reasoning. The proposed model is evaluated on the TBX-Att dataset and will serve as a solid baseline for future research. The code and data will be available at https://github.com/GangmingZhao/tb-attribute-weak-localization.

Chaowei Fang, Dingwen Zhang, Liang Wang et al. · eth-zurich

Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis. Higher resolution helps to capture more detailed content, but typically induces to lower signal-to-noise ratio and longer scanning time. To this end, MR image super-resolution has become a widely-interested topic in recent times. Existing works establish extensive deep models with the conventional architectures based on convolutional neural networks (CNN). In this work, to further advance this research field, we make an early effort to build a Transformer-based MR image super-resolution framework, with careful designs on exploring valuable domain prior knowledge. Specifically, we consider two-fold domain priors including the high-frequency structure prior and the inter-modality context prior, and establish a novel Transformer architecture, called Cross-modality high-frequency Transformer (Cohf-T), to introduce such priors into super-resolving the low-resolution (LR) MR images. Experiments on two datasets indicate that Cohf-T achieves new state-of-the-art performance.

Junwen Pan, Pengfei Zhu, Kaihua Zhang et al.

Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently. Most leading WSSS methods employ a sophisticated multi-stage training strategy to estimate pseudo-labels as precise as possible, but they suffer from high model complexity. In contrast, there exists another research line that trains a single network with image-level labels in one training cycle. However, such a single-stage strategy often performs poorly because of the compounding effect caused by inaccurate pseudo-label estimation. To address this issue, this paper presents a Self-supervised Low-Rank Network (SLRNet) for single-stage WSSS and SSSS. The SLRNet uses cross-view self-supervision, that is, it simultaneously predicts several complementary attentive LR representations from different views of an image to learn precise pseudo-labels. Specifically, we reformulate the LR representation learning as a collective matrix factorization problem and optimize it jointly with the network learning in an end-to-end manner. The resulting LR representation deprecates noisy information while capturing stable semantics across different views, making it robust to the input variations, thereby reducing overfitting to self-supervision errors. The SLRNet can provide a unified single-stage framework for various label-efficient semantic segmentation settings: 1) WSSS with image-level labeled data, 2) SSSS with a few pixel-level labeled data, and 3) SSSS with a few pixel-level labeled data and many image-level labeled data. Extensive experiments on the Pascal VOC 2012, COCO, and L2ID datasets demonstrate that our SLRNet outperforms both state-of-the-art WSSS and SSSS methods with a variety of different settings, proving its good generalizability and efficacy.

Xianmin Chen, Longfei Han, Peiliang Huang et al.

Low-light image enhancement, particularly in cross-domain tasks such as mapping from the raw domain to the sRGB domain, remains a significant challenge. Many deep learning-based methods have been developed to address this issue and have shown promising results in recent years. However, single-stage methods, which attempt to unify the complex mapping across both domains, leading to limited denoising performance. In contrast, existing two-stage approaches typically overlook the characteristic of demosaicing within the Image Signal Processing (ISP) pipeline, leading to color distortions under varying lighting conditions, especially in low-light scenarios. To address these issues, we propose a novel Mamba-based method customized for low light RAW images, called RAWMamba, to effectively handle raw images with different CFAs. Furthermore, we introduce a Retinex Decomposition Module (RDM) grounded in Retinex prior, which decouples illumination from reflectance to facilitate more effective denoising and automatic non-linear exposure correction, reducing the effect of manual linear illumination enhancement. By bridging demosaicing and denoising, better enhancement for low light RAW images is achieved. Experimental evaluations conducted on public datasets SID and MCR demonstrate that our proposed RAWMamba achieves state-of-the-art performance on cross-domain mapping. The code is available at https://github.com/Cynicarlos/RetinexRawMamba.

De Cheng, Gerong Wang, Bo Wang et al.

Zero-shot learning (ZSL) aims to learn models that can recognize unseen image semantics based on the training of data with seen semantics. Recent studies either leverage the global image features or mine discriminative local patch features to associate the extracted visual features to the semantic attributes. However, due to the lack of the necessary top-down guidance and semantic alignment for ensuring the model attending to the real attribute-correlation regions, these methods still encounter a significant semantic gap between the visual modality and the attribute modality, which makes their prediction on unseen semantics unreliable. To solve this problem, this paper establishes a novel transformer encoder-decoder model, called hybrid routing transformer (HRT). In HRT encoder, we embed an active attention, which is constructed by both the bottom-up and the top-down dynamic routing pathways to generate the attribute-aligned visual feature. While in HRT decoder, we use static routing to calculate the correlation among the attribute-aligned visual features, the corresponding attribute semantics, and the class attribute vectors to generate the final class label predictions. This design makes the presented transformer model a hybrid of 1) top-down and bottom-up attention pathways and 2) dynamic and static routing pathways. Comprehensive experiments on three widely-used benchmark datasets, namely CUB, SUN, and AWA2, are conducted. The obtained experimental results demonstrate the effectiveness of the proposed method.

Hao Li, Dingwen Zhang, Nian Liu et al.

Recently, inspired by DETR variants, query-based end-to-end instance segmentation (QEIS) methods have outperformed CNN-based models on large-scale datasets. Yet they would lose efficacy when only a small amount of training data is available since it's hard for the crucial queries/kernels to learn localization and shape priors. To this end, this work offers a novel unsupervised pre-training solution for low-data regimes. Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models by giving Saliency Prompt for queries/kernels. Our method contains three parts: 1) Saliency Masks Proposal is responsible for generating pseudo masks from unlabeled images based on the saliency mechanism. 2) Prompt-Kernel Matching transfers pseudo masks into prompts and injects the corresponding localization and shape priors to the best-matched kernels. 3) Kernel Supervision is applied to supply supervision at the kernel level for robust learning. From a practical perspective, our pre-training method helps QEIS models achieve a similar convergence speed and comparable performance with CNN-based models in low-data regimes. Experimental results show that our method significantly boosts several QEIS models on three datasets. Code will be made available.

De Cheng, Yan Li, Dingwen Zhang et al.

Single image dehazing as a fundamental low-level vision task, is essential for the development of robust intelligent surveillance system. In this paper, we make an early effort to consider dehazing robustness under variational haze density, which is a realistic while under-studied problem in the research filed of singe image dehazing. To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios. Specifically, the dehazing network is optimized under the consistency-regularized framework with the proposed Contrast-Assisted Reconstruction Loss (CARL). The CARL can fully exploit the negative information to facilitate the traditional positive-orient dehazing objective function, by squeezing the dehazed image to its clean target from different directions. Meanwhile, the consistency regularization keeps consistent outputs given multi-level hazy images, thus improving the model robustness. Extensive experimental results on two synthetic and three real-world datasets demonstrate that our method significantly surpasses the state-of-the-art approaches.

Hao Li, Dingwen Zhang, Yalun Dai et al.

Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering" task, to build semantic NeRFs. However, by rendering semantic/instance labels per pixel without considering the contextual information of the rendered image, these methods usually suffer from unclear boundary segmentation and abnormal segmentation of pixels within an object. To solve this problem, we propose Generalized Perception NeRF (GP-NeRF), a novel pipeline that makes the widely used segmentation model and NeRF work compatibly under a unified framework, for facilitating context-aware 3D scene perception. To accomplish this goal, we introduce transformers to aggregate radiance as well as semantic embedding fields jointly for novel views and facilitate the joint volumetric rendering of both fields. In addition, we propose two self-distillation mechanisms, i.e., the Semantic Distill Loss and the Depth-Guided Semantic Distill Loss, to enhance the discrimination and quality of the semantic field and the maintenance of geometric consistency. In evaluation, we conduct experimental comparisons under two perception tasks (\textit{i.e.} semantic and instance segmentation) using both synthetic and real-world datasets. Notably, our method outperforms SOTA approaches by 6.94\%, 11.76\%, and 8.47\% on generalized semantic segmentation, finetuning semantic segmentation, and instance segmentation, respectively.

Lechao Cheng, Chaowei Fang, Dingwen Zhang et al.

Significant progress has been made in learning image classification neural networks under long-tail data distribution using robust training algorithms such as data re-sampling, re-weighting, and margin adjustment. Those methods, however, ignore the impact of data imbalance on feature normalization. The dominance of majority classes (head classes) in estimating statistics and affine parameters causes internal covariate shifts within less-frequent categories to be overlooked. To alleviate this challenge, we propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. In addition, a moving average-based expectation maximization (EM) algorithm is employed to estimate the statistical parameters of multiple Gaussian distributions. However, the EM algorithm is sensitive to initialization and can easily become stuck in local minima where the multiple Gaussian components continue to focus on majority classes. To tackle this issue, we developed a dual-path learning framework that employs class-aware split feature normalization to diversify the estimated Gaussian distributions, allowing the Gaussian components to fit with training samples of less-frequent classes more comprehensively. Extensive experiments on commonly used datasets demonstrated that the proposed method outperforms existing methods on long-tailed image classification.

Chaowei Fang, Dingwen Zhang, Wen Zheng et al.

Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are devised to address the data imbalance problem by biasing the training process towards less frequent classes. However, they usually evaluate the performance on a balanced testing set or multiple independent testing sets having distinct distributions with the training data. Considering the testing data may have arbitrary distributions, existing evaluation strategies are unable to reflect the actual classification performance objectively. We set up novel evaluation benchmarks based on a series of testing sets with evolving distributions. A corpus of metrics are designed for measuring the accuracy, robustness, and bounds of algorithms for learning with long-tailed distribution. Based on our benchmarks, we re-evaluate the performance of existing methods on CIFAR10 and CIFAR100 datasets, which is valuable for guiding the selection of data rebalancing techniques. We also revisit existing methods and categorize them into four types including data balancing, feature balancing, loss balancing, and prediction balancing, according the focused procedure during the training pipeline.

Chaowei Fang, Lechao Cheng, Huiyan Qi et al.

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To this end, this paper makes an early effort to tackle the image classification task with both long-tailed distribution and label noise. Existing noise-robust learning methods cannot work in this scenario as it is challenging to differentiate noisy samples from clean samples of tail classes. To deal with this problem, we propose a new learning paradigm based on matching between inferences on weak and strong data augmentations to screen out noisy samples and introduce a leave-noise-out regularization to eliminate the effect of the recognized noisy samples. Furthermore, we incorporate a novel prediction penalty based on online prior distribution to avoid bias towards head classes. This mechanism has superiority in capturing the class fitting degree in realtime compared to the existing long-tail classification methods. Exhaustive experiments demonstrate that the proposed method outperforms state-of-the-art algorithms that address the distribution imbalance problem in long-tailed classification under noisy labels.

Long Li, Nian Liu, Dingwen Zhang et al.

Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.

Haosong Peng, Hao Li, Jiaqi Chen et al.

While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round players capable of generalizing robustly across diverse downstream tasks, arbitrary viewpoints, shifting scene domains, varying input densities, and specific hardware constraints? Answering this overarching question requires a holistic assessment, yet current models are mainly evaluated on specific domains for which they were specifically designed or trained. Such evaluations are intrinsically limited by narrow paradigm coverage, limited scene domains, and arbitrary frame sampling, making it fundamentally difficult to assess their true generalization capabilities. To address this gap, we present SpatialBench, a cross-paradigm, domain-diverse benchmark for spatial foundation models with deterministic sampling. SpatialBench features unprecedented scale and rigorous deterministic design, comprising 19 datasets and 546 scenes across 5 diverse spatial domains. It comprehensively evaluates 41 models across 6 paradigms on 5 task suites under 4 different input density settings. Our extensive evaluation reveals that current models are not yet all-round players, and uncovers crucial insights for future advancement. Specifically, we demonstrate that full-context attention maximizes accuracy while bounded-memory strategies unlock long-sequence scalability. Moreover, our empirical evaluations in challenging embodied and egocentric tasks demonstrate that strict domain alignment and high data quality are far more critical to performance than simple dataset scaling. Furthermore, to address the largest data gap identified in our analysis, we go beyond evaluation by introducing a large-scale dataset, DA-Next-5M, and a strong baseline model, DA-Next, pushing the boundaries of spatial representation learning.

Di Wu, Feng Yang, Wenhui Zhao et al.

Multi-view 3D object detection is a fundamental task in autonomous driving perception, where achieving a balance between detection accuracy and computational efficiency remains crucial. Sparse query-based 3D detectors efficiently aggregate object-relevant features from multi-view images through a set of learnable queries, offering a concise and end-to-end detection paradigm. Building on this foundation, MV2D leverages 2D detection results to provide high-quality object priors for query initialization, enabling higher precision and recall. However, the inherent depth ambiguity in single-frame 2D detections still limits the accuracy of 3D query generation. To address this issue, we propose StereoMV2D, a unified framework that integrates temporal stereo modeling into the 2D detection-guided multi-view 3D detector. By exploiting cross-temporal disparities of the same object across adjacent frames, StereoMV2D enhances depth perception and refines the query priors, while performing all computations efficiently within 2D regions of interest (RoIs). Furthermore, a dynamic confidence gating mechanism adaptively evaluates the reliability of temporal stereo cues through learning statistical patterns derived from the inter-frame matching matrix together with appearance consistency, ensuring robust detection under object appearance and occlusion. Extensive experiments on the nuScenes and Argoverse 2 datasets demonstrate that StereoMV2D achieves superior detection performance without incurring significant computational overhead. Code will be available at https://github.com/Uddd821/StereoMV2D.

De Cheng, Yanling Ji, Dong Gong et al.

In real-world applications, image degeneration caused by adverse weather is always complex and changes with different weather conditions from days and seasons. Systems in real-world environments constantly encounter adverse weather conditions that are not previously observed. Therefore, it practically requires adverse weather removal models to continually learn from incrementally collected data reflecting various degeneration types. Existing adverse weather removal approaches, for either single or multiple adverse weathers, are mainly designed for a static learning paradigm, which assumes that the data of all types of degenerations to handle can be finely collected at one time before a single-phase learning process. They thus cannot directly handle the incremental learning requirements. To address this issue, we made the earliest effort to investigate the continual all-in-one adverse weather removal task, in a setting closer to real-world applications. Specifically, we develop a novel continual learning framework with effective knowledge replay (KR) on a unified network structure. Equipped with a principal component projection and an effective knowledge distillation mechanism, the proposed KR techniques are tailored for the all-in-one weather removal task. It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure. Extensive experimental results demonstrate the effectiveness of the proposed method to deal with this challenging task, which performs competitively to existing dedicated or joint training image restoration methods. Our code is available at https://github.com/xiaojihh/CL_all-in-one.

Yuzhu Wang, Lechao Cheng, Chaowei Fang et al.

Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often encounter challenges like prompt initialization, prompt length, and subpar performance in self-supervised pretraining, hindering successful contextual adaptation. This study commences by exploring the correlation evolvement between prompts and patch tokens during proficient training. Inspired by the observation that the prompt tokens tend to share high mutual information with patch tokens, we propose initializing prompts with downstream token prototypes. The strategic initialization, a stand-in for the previous initialization, substantially improves performance in fine-tuning. To refine further, we optimize token construction with a streamlined pipeline that maintains excellent performance with almost no increase in computational expenses compared to VPT. Exhaustive experiments show our proposed approach outperforms existing methods by a remarkable margin. For instance, it surpasses full fine-tuning in 19 out of 24 tasks, using less than 0.4% of learnable parameters on the FGVC and VTAB-1K benchmarks. Notably, our method significantly advances the adaptation for self-supervised pretraining, achieving impressive task performance gains of at least 10% to 30%. Besides, the experimental results demonstrate the proposed SPT is robust to prompt lengths and scales well with model capacity and training data size. We finally provide an insightful exploration into the amount of target data facilitating the adaptation of pre-trained models to downstream tasks. The code is available at https://github.com/WangYZ1608/Self-Prompt-Tuning.

Long Li, Shuichen Ji, Ziyang Luo et al.

We present the first unified framework that jointly handles three operationally heterogeneous saliency tasks, eg, SOD, CoSOD, and SIS, by casting each as a Chain-of-Thought (CoT) reasoning process in a Vision-Language Model (VLM) to bridge task heterogeneity. CoT training follows a two-stage paradigm: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). To enhance CoT quality in RL, we propose Confidence-Guided Policy Optimization (CGPO), a lightweight single-sample algorithm that leverages the discrepancy between reward and model confidence as a per-sample advantage signal. This design naturally focuses updates on informative responses while eliminating group sampling, thereby addressing GRPO's key limitations: confidence-agnostic learning, signal dilution, and prohibitive computational overhead. We also introduce an "output-to-reasoning" strategy to construct high-fidelity SFT data that ensures logical consistency with ground-truth masks. Experiments show our model matches or outperforms specialized SOTA methods and strong closed-source VLMs across all tasks, especially achieving an S-measure of 0.899 on CoCA for CoSOD, surpassing the prior best by 8.0 percentage points, despite using far less training data.

Dingwen Zhang, Hao Li, Diqi He et al.

In recent times, following the paradigm of DETR (DEtection TRansformer), query-based end-to-end instance segmentation (QEIS) methods have exhibited superior performance compared to CNN-based models, particularly when trained on large-scale datasets. Nevertheless, the effectiveness of these QEIS methods diminishes significantly when confronted with limited training data. This limitation arises from their reliance on substantial data volumes to effectively train the pivotal queries/kernels that are essential for acquiring localization and shape priors. To address this problem, we propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-Vision Prompts (UPLVP), which improves QEIS models' instance segmentation by bringing language-vision prompts to queries/kernels. Our method consists of three parts: (1) Masks Proposal: Utilizes language-vision models to generate pseudo masks based on unlabeled images. (2) Prompt-Kernel Matching: Converts pseudo masks into prompts and injects the best-matched localization and shape features to their corresponding kernels. (3) Kernel Supervision: Formulates supervision for pre-training at the kernel level to ensure robust learning. With the help of our pre-training method, QEIS models can converge faster and perform better than CNN-based models in low-data regimes. Experimental evaluations conducted on MS COCO, Cityscapes, and CTW1500 datasets indicate that the QEIS models' performance can be significantly improved when pre-trained with our method. Code will be available at: https://github.com/lifuguan/UPLVP.

Modi Jin, Yiming Zhang, Boyuan Sun et al.

This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain concerns because of their reliance on AI-generated chain-of-thought (CoT) data and training strategies, which conflict with geographic characteristics. To address these issues, we first introduce GeoSeek, a new geolocation dataset comprising CoT data annotated by geographic experts and professional players. We further thoroughly explore the inherent characteristics of geographic tasks and propose a geo-similarity reward and a consistency reward assessed by a consistency agent to assist training. This encourages the model to converge towards correct answers from a geographic perspective while ensuring the integrity and consistency of its reasoning process. Experimental results show that GeoAgent outperforms existing methods and a series of general VLLMs across multiple grains, while generating reasoning that closely aligns with humans.

Yi Liu, Chengxin Li, Xiaohui Dong et al.

Achieving joint learning of Salient Object Detection (SOD) and Camouflaged Object Detection (COD) is extremely challenging due to their distinct object characteristics, i.e., saliency and camouflage. The only preliminary research treats them as two contradictory tasks, training models on large-scale labeled data alternately for each task and assessing them independently. However, such task-specific mechanisms fail to meet real-world demands for addressing unknown tasks effectively. To address this issue, in this paper, we pioneer a task-agnostic framework to unify SOD and COD. To this end, inspired by the agreeable nature of binary segmentation for SOD and COD, we propose a Contrastive Distillation Paradigm (CDP) to distil the foreground from the background, facilitating the identification of salient and camouflaged objects amidst their surroundings. To probe into the contribution of our CDP, we design a simple yet effective contextual decoder involving the interval-layer and global context, which achieves an inference speed of 67 fps. Besides the supervised setting, our CDP can be seamlessly integrated into unsupervised settings, eliminating the reliance on extensive human annotations. Experiments on public SOD and COD datasets demonstrate the superiority of our proposed framework in both supervised and unsupervised settings, compared with existing state-of-the-art approaches. Code is available on https://github.com/liuyi1989/Seamless-Detection.

Yuning Gong, Yifei Liu, Yifan Zhan et al.

Neural rendering, particularly 3D Gaussian Splatting (3DGS), has evolved rapidly and become a key component for building world models. However, existing viewer solutions remain fragmented, heavy, or constrained by legacy pipelines, resulting in high deployment friction and limited support for dynamic content and generative models. In this work, we present Visionary, an open, web-native platform for real-time various Gaussian Splatting and meshes rendering. Built on an efficient WebGPU renderer with per-frame ONNX inference, Visionary enables dynamic neural processing while maintaining a lightweight, "click-to-run" browser experience. It introduces a standardized Gaussian Generator contract, which not only supports standard 3DGS rendering but also allows plug-and-play algorithms to generate or update Gaussians each frame. Such inference also enables us to apply feedforward generative post-processing. The platform further offers a plug in three.js library with a concise TypeScript API for seamless integration into existing web applications. Experiments show that, under identical 3DGS assets, Visionary achieves superior rendering efficiency compared to current Web viewers due to GPU-based primitive sorting. It already supports multiple variants, including MLP-based 3DGS, 4DGS, neural avatars, and style transformation or enhancement networks. By unifying inference and rendering directly in the browser, Visionary significantly lowers the barrier to reproduction, comparison, and deployment of 3DGS-family methods, serving as a unified World Model Carrier for both reconstructive and generative paradigms.

De Cheng, Lingfeng He, Nannan Wang et al.

Unsupervised visible-infrared person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning. Previous methods unify pseudo-labels of cross-modality images through label association algorithms and then design contrastive learning framework for global feature learning. However, these methods overlook the cross-modality variations in feature representation and pseudo-label distributions brought by fine-grained patterns. This insight results in insufficient modality-shared learning when only global features are optimized. To address this issue, we propose a Semantic-Aligned Learning with Collaborative Refinement (SALCR) framework, which builds up optimization objective for specific fine-grained patterns emphasized by each modality, thereby achieving complementary alignment between the label distributions of different modalities. Specifically, we first introduce a Dual Association with Global Learning (DAGI) module to unify the pseudo-labels of cross-modality instances in a bi-directional manner. Afterward, a Fine-Grained Semantic-Aligned Learning (FGSAL) module is carried out to explore part-level semantic-aligned patterns emphasized by each modality from cross-modality instances. Optimization objective is then formulated based on the semantic-aligned features and their corresponding label space. To alleviate the side-effects arising from noisy pseudo-labels, we propose a Global-Part Collaborative Refinement (GPCR) module to mine reliable positive sample sets for the global and part features dynamically and optimize the inter-instance relationships. Extensive experiments demonstrate the effectiveness of the proposed method, which achieves superior performances to state-of-the-art methods. Our code is available at \href{https://github.com/FranklinLingfeng/code-for-SALCR}.

Zhengyu Zou, Jingfeng Li, Hao Li et al.

Neural Radiance Fields (NeRFs) implicitly model continuous three-dimensional scenes using a set of images with known camera poses, enabling the rendering of photorealistic novel views. However, existing NeRF-based methods encounter challenges in applications such as autonomous driving and robotic perception, primarily due to the difficulty of capturing accurate camera poses and limitations in handling large-scale dynamic environments. To address these issues, we propose Vision-only Dynamic NeRF (VDNeRF), a method that accurately recovers camera trajectories and learns spatiotemporal representations for dynamic urban scenes without requiring additional camera pose information or expensive sensor data. VDNeRF employs two separate NeRF models to jointly reconstruct the scene. The static NeRF model optimizes camera poses and static background, while the dynamic NeRF model incorporates the 3D scene flow to ensure accurate and consistent reconstruction of dynamic objects. To address the ambiguity between camera motion and independent object motion, we design an effective and powerful training framework to achieve robust camera pose estimation and self-supervised decomposition of static and dynamic elements in a scene. Extensive evaluations on mainstream urban driving datasets demonstrate that VDNeRF surpasses state-of-the-art NeRF-based pose-free methods in both camera pose estimation and dynamic novel view synthesis.

Fangwen Wu, Lechao Cheng, Shengeng Tang et al.

Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones. Balancing flexibility and stability remains a significant challenge, particularly when the task ID is unknown. To address this, our study reveals that the gap in feature distribution between novel and existing tasks is primarily driven by differences in mean and covariance moments. Building on this insight, we propose a novel semantic drift calibration method that incorporates mean shift compensation and covariance calibration. Specifically, we calculate each class's mean by averaging its sample embeddings and estimate task shifts using weighted embedding changes based on their proximity to the previous mean, effectively capturing mean shifts for all learned classes with each new task. We also apply Mahalanobis distance constraint for covariance calibration, aligning class-specific embedding covariances between old and current networks to mitigate the covariance shift. Additionally, we integrate a feature-level self-distillation approach to enhance generalization. Comprehensive experiments on commonly used datasets demonstrate the effectiveness of our approach. The source code is available at \href{https://github.com/fwu11/MACIL.git}{https://github.com/fwu11/MACIL.git}.

Di Wu, Feng Yang, Benlian Xu et al.

The application of vision-based multi-view environmental perception system has been increasingly recognized in autonomous driving technology, especially the BEV-based models. Current state-of-the-art solutions primarily encode image features from each camera view into the BEV space through explicit or implicit depth prediction. However, these methods often overlook the structured correlations among different parts of objects in 3D space and the fact that different categories of objects often occupy distinct local height ranges. For example, trucks appear at higher elevations, whereas traffic cones are near the ground. In this work, we propose a novel approach that decouples feature sampling in the \textbf{BEV} grid queries paradigm into \textbf{H}orizontal feature aggregation and \textbf{V}ertical adaptive height-aware reference point sampling (HV-BEV), aiming to improve both the aggregation of objects' complete information and awareness of diverse objects' height distribution. Specifically, a set of relevant neighboring points is dynamically constructed for each 3D reference point on the ground-aligned horizontal plane, enhancing the association of the same instance across different BEV grids, especially when the instance spans multiple image views around the vehicle. Additionally, instead of relying on uniform sampling within a fixed height range, we introduce a height-aware module that incorporates historical information, enabling the reference points to adaptively focus on the varying heights at which objects appear in different scenes. Extensive experiments validate the effectiveness of our proposed method, demonstrating its superior performance over the baseline across the nuScenes dataset. Moreover, our best-performing model achieves a remarkable 50.5\% mAP and 59.8\% NDS on the nuScenes testing set. The code is available at https://github.com/Uddd821/HV-BEV.

Xianmin Chen, Peiliang Huang, Longfei Han et al.

With the rapid development of deep learning, low-light RAW image enhancement (LLRIE) has achieved remarkable progress. However, the challenge that how to simultaneously achieve strong enhancement quality and high efficiency still remains. Leveraging the inherent efficiency of Channel Attention and Mamba, we introduce a Hierarchical Mixing Architecture (HiMA), a hybrid LLRIE framework built upon two core modules. Specifically, we introduce Large Scale Block (LSB) for upper layers and Small Scale Block (SSB) for lower layers that reduce the parameters while improve the performance. Based on this framework, we also introduce a novel Local Distribution Adjustment (LoDA) module that adaptively aligns local feature statistics in a content-aware manner by learning to adjust regional luminance and contrast distributions. Moreover, to alleviate the domain ambiguity commonly observed in existing LLRIE pipelines, we design a Multi-Prior Fusion (MPF) module that leverages three complementary priors extracted from the first stage of the hybrid architecture to maintain domain consistency. Extensive experiments on multiple public benchmarks demonstrate that our approach outperforms state-of-the-art methods, delivering superior performance with fewer parameters. Code is available at https://github.com/Cynicarlos/HiMA.

Jiaqi Chen, Xinhao Ji, Yuanyuan Gao et al.

Neural scene representations, such as 3D Gaussian Splatting (3DGS), have enabled high-quality neural rendering; however, their large storage and transmission costs hinder deployment in resource-constrained environments. Existing compression methods either rely on costly optimization, which is slow and scene-specific, or adopt training-free pruning and quantization, which degrade rendering quality under high compression ratios. In contrast, recent data-driven approaches provide a promising direction to overcome this trade-off, enabling efficient compression while preserving high rendering quality. We introduce ExGS, a novel feed-forward framework that unifies Universal Gaussian Compression (UGC) with GaussPainter for Extreme 3DGS compression. UGC performs re-optimization-free pruning to aggressively reduce Gaussian primitives while retaining only essential information, whereas GaussPainter leverages powerful diffusion priors with mask-guided refinement to restore high-quality renderings from heavily pruned Gaussian scenes. Unlike conventional inpainting, GaussPainter not only fills in missing regions but also enhances visible pixels, yielding substantial improvements in degraded renderings. To ensure practicality, it adopts a lightweight VAE and a one-step diffusion design, enabling real-time restoration. Our framework can even achieve over 100X compression (reducing a typical 354.77 MB model to about 3.31 MB) while preserving fidelity and significantly improving image quality under challenging conditions. These results highlight the central role of diffusion priors in bridging the gap between extreme compression and high-quality neural rendering. Our code repository will be released at: https://github.com/chenttt2001/ExGS

Huiqian Li, Dingwen Zhang, Jieru Yao et al.

Polyp segmentation plays a pivotal role in colorectal cancer diagnosis. Recently, the emergence of the Segment Anything Model (SAM) has introduced unprecedented potential for polyp segmentation, leveraging its powerful pre-training capability on large-scale datasets. However, due to the domain gap between natural and endoscopy images, SAM encounters two limitations in achieving effective performance in polyp segmentation. Firstly, its Transformer-based structure prioritizes global and low-frequency information, potentially overlooking local details, and introducing bias into the learned features. Secondly, when applied to endoscopy images, its poor out-of-distribution (OOD) performance results in substandard predictions and biased confidence output. To tackle these challenges, we introduce a novel approach named Augmented SAM for Polyp Segmentation (ASPS), equipped with two modules: Cross-branch Feature Augmentation (CFA) and Uncertainty-guided Prediction Regularization (UPR). CFA integrates a trainable CNN encoder branch with a frozen ViT encoder, enabling the integration of domain-specific knowledge while enhancing local features and high-frequency details. Moreover, UPR ingeniously leverages SAM's IoU score to mitigate uncertainty during the training procedure, thereby improving OOD performance and domain generalization. Extensive experimental results demonstrate the effectiveness and utility of the proposed method in improving SAM's performance in polyp segmentation. Our code is available at https://github.com/HuiqianLi/ASPS.

Yuqing Wang, Zhongling Huang, Shuxin Yang et al.

PolSAR data presents unique challenges due to its rich and complex characteristics. Existing data representations, such as complex-valued data, polarimetric features, and amplitude images, are widely used. However, these formats often face issues related to usability, interpretability, and data integrity. Most feature extraction networks for PolSAR are small, limiting their ability to capture features effectively. To address these issues, We propose the Polarimetric Scattering Mechanism-Informed SAM (PolSAM), an enhanced Segment Anything Model (SAM) that integrates domain-specific scattering characteristics and a novel prompt generation strategy. PolSAM introduces Microwave Vision Data (MVD), a lightweight and interpretable data representation derived from polarimetric decomposition and semantic correlations. We propose two key components: the Feature-Level Fusion Prompt (FFP), which fuses visual tokens from pseudo-colored SAR images and MVD to address modality incompatibility in the frozen SAM encoder, and the Semantic-Level Fusion Prompt (SFP), which refines sparse and dense segmentation prompts using semantic information. Experimental results on the PhySAR-Seg datasets demonstrate that PolSAM significantly outperforms existing SAM-based and multimodal fusion models, improving segmentation accuracy, reducing data storage, and accelerating inference time. The source code and datasets will be made publicly available at https://github.com/XAI4SAR/PolSAM.

Guangyu Guo, Dingwen Zhang, Longfei Han et al.

Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size. Therefore, we propose Pixel Distillation that extends knowledge distillation into the input level while simultaneously breaking architecture constraints. Such a scheme can achieve flexible cost control for deployment, as it allows the system to adjust both network architecture and image quality according to the overall requirement of resources. Specifically, we first propose an input spatial representation distillation (ISRD) mechanism to transfer spatial knowledge from large images to student's input module, which can facilitate stable knowledge transfer between CNN and ViT. Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge. Finally, we adapt pixel distillation to object detection via an aligned feature for preservation (AFP) strategy for TAS, which aligns output dimensions of detectors at each stage by manipulating features and anchors of the assistant. Comprehensive experiments on image classification and object detection demonstrate the effectiveness of our method. Code is available at https://github.com/gyguo/PixelDistillation.

Le Yang, Junwei Han, Tao Zhao et al.

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an action-click supervision framework. It requires similar annotation costs but can steadily improve the localization performance when compared to the conventional weakly supervised methods. In this paper, by revealing that the performance bottleneck of the existing approaches mainly comes from the background errors, we find that a stronger action localizer can be trained with labels on the background video frames rather than those on the action frames. To this end, we convert the action-click supervision to the background-click supervision and develop a novel method, called BackTAL. Specifically, BackTAL implements two-fold modeling on the background video frames, i.e. the position modeling and the feature modeling. In position modeling, we not only conduct supervised learning on the annotated video frames but also design a score separation module to enlarge the score differences between the potential action frames and backgrounds. In feature modeling, we propose an affinity module to measure frame-specific similarities among neighboring frames and dynamically attend to informative neighbors when calculating temporal convolution. Extensive experiments on three benchmarks are conducted, which demonstrate the high performance of the established BackTAL and the rationality of the proposed background-click supervision. Code is available at https://github.com/VividLe/BackTAL.

Yan Li, De Cheng, Jiande Sun et al.

Single image dehazing is a prerequisite which affects the performance of many computer vision tasks and has attracted increasing attention in recent years. However, most existing dehazing methods emphasize more on haze removal but less on the detail recovery of the dehazed images. In this paper, we propose a single image dehazing method with an independent Detail Recovery Network (DRN), which considers capturing the details from the input image over a separate network and then integrates them into a coarse dehazed image. The overall network consists of two independent networks, named DRN and the dehazing network respectively. Specifically, the DRN aims to recover the dehazed image details through local and global branches respectively. The local branch can obtain local detail information through the convolution layer and the global branch can capture more global information by the Smooth Dilated Convolution (SDC). The detail feature map is fused into the coarse dehazed image to obtain the dehazed image with rich image details. Besides, we integrate the DRN, the physical-model-based dehazing network and the reconstruction loss into an end-to-end joint learning framework. Extensive experiments on the public image dehazing datasets (RESIDE-Indoor, RESIDE-Outdoor and the TrainA-TestA) illustrate the effectiveness of the modules in the proposed method and show that our method outperforms the state-of-the-art dehazing methods both quantitatively and qualitatively. The code is released in https://github.com/YanLi-LY/Dehazing-DRN.

Jie Lian, Jingyu Liu, Shu Zhang et al.

Instance level detection and segmentation of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images. Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN. The SAR-Net consists of three relation modules: 1. the anatomical structure relation module encoding spatial relations between diseases and anatomical parts. 2. the contextual relation module aggregating clues based on query-key pair of disease RoI and lung fields. 3. the disease relation module propagating co-occurrence and causal relations into disease proposals. Towards making a practical system, we also provide ChestX-Det, a chest X-Ray dataset with instance-level annotations (boxes and masks). ChestX-Det is a subset of the public dataset NIH ChestX-ray14. It contains ~3500 images of 13 common disease categories labeled by three board-certified radiologists. We evaluate our SAR-Net on it and another dataset DR-Private. Experimental results show that it can enhance the strong baseline of Mask R-CNN with significant improvements. The ChestX-Det is released at https://github.com/Deepwise-AILab/ChestX-Det-Dataset.

Dingwen Zhang, Haibin Tian, Jungong Han

Detecting and segmenting salient objects from given image scenes has received great attention in recent years. A fundamental challenge in training the existing deep saliency detection models is the requirement of large amounts of annotated data. While gathering large quantities of training data becomes cheap and easy, annotating the data is an expensive process in terms of time, labor and human expertise. To address this problem, this paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only, thus dramatically alleviating human labor in training models. To this end, we name this task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario. Essentially, APL is derived from the self-paced learning (SPL) regime but it infers the robust learning pace through the data-driven adversarial learning mechanism rather than the heuristic design of the learning regularizer. Comprehensive experiments on four widely-used benchmark datasets demonstrate that the proposed method can effectively approach to the existing supervised deep salient object detection models with only 1k human-annotated training images. The project page is available at https://github.com/hb-stone/FC-SOD.

Dingwen Zhang, Bo Wang, Gerong Wang et al.

Onfocus detection aims at identifying whether the focus of the individual captured by a camera is on the camera or not. Based on the behavioral research, the focus of an individual during face-to-camera communication leads to a special type of eye contact, i.e., the individual-camera eye contact, which is a powerful signal in social communication and plays a crucial role in recognizing irregular individual status (e.g., lying or suffering mental disease) and special purposes (e.g., seeking help or attracting fans). Thus, developing effective onfocus detection algorithms is of significance for assisting the criminal investigation, disease discovery, and social behavior analysis. However, the review of the literature shows that very few efforts have been made toward the development of onfocus detector due to the lack of large-scale public available datasets as well as the challenging nature of this task. To this end, this paper engages in the onfocus detection research by addressing the above two issues. Firstly, we build a large-scale onfocus detection dataset, named as the OnFocus Detection In the Wild (OFDIW). It consists of 20,623 images in unconstrained capture conditions (thus called ``in the wild'') and contains individuals with diverse emotions, ages, facial characteristics, and rich interactions with surrounding objects and background scenes. On top of that, we propose a novel end-to-end deep model, i.e., the eye-context interaction inferring network (ECIIN), for onfocus detection, which explores eye-context interaction via dynamic capsule routing. Finally, comprehensive experiments are conducted on the proposed OFDIW dataset to benchmark the existing learning models and demonstrate the effectiveness of the proposed ECIIN. The project (containing both datasets and codes) is at https://github.com/wintercho/focus.

Chaowei Fang, Haibin Tian, Dingwen Zhang et al.

With the goal of identifying pixel-wise salient object regions from each input image, salient object detection (SOD) has been receiving great attention in recent years. One kind of mainstream SOD methods is formed by a bottom-up feature encoding procedure and a top-down information decoding procedure. While numerous approaches have explored the bottom-up feature extraction for this task, the design on top-down flows still remains under-studied. To this end, this paper revisits the role of top-down modeling in salient object detection and designs a novel densely nested top-down flows (DNTDF)-based framework. In every stage of DNTDF, features from higher levels are read in via the progressive compression shortcut paths (PCSP). The notable characteristics of our proposed method are as follows. 1) The propagation of high-level features which usually have relatively strong semantic information is enhanced in the decoding procedure; 2) With the help of PCSP, the gradient vanishing issues caused by non-linear operations in top-down information flows can be alleviated; 3) Thanks to the full exploration of high-level features, the decoding process of our method is relatively memory efficient compared against those of existing methods. Integrating DNTDF with EfficientNet, we construct a highly light-weighted SOD model, with very low computational complexity. To demonstrate the effectiveness of the proposed model, comprehensive experiments are conducted on six widely-used benchmark datasets. The comparisons to the most state-of-the-art methods as well as the carefully-designed baseline models verify our insights on the top-down flow modeling for SOD. The code of this paper is available at https://github.com/new-stone-object/DNTD.

Mingchen Zhuge, Deng-Ping Fan, Nian Liu et al.

Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level. Specifically, at the micro level, the model should highlight all parts that belong to a certain salient object. Meanwhile, at the macro level, the model needs to discover all salient objects in a given image. To facilitate integrity learning for SOD, we design a novel Integrity Cognition Network (ICON), which explores three important components for learning strong integrity features. 1) Unlike existing models, which focus more on feature discriminability, we introduce a diverse feature aggregation (DFA) component to aggregate features with various receptive fields (i.e., kernel shape and context) and increase feature diversity. Such diversity is the foundation for mining the integral salient objects. 2) Based on the DFA features, we introduce an integrity channel enhancement (ICE) component with the goal of enhancing feature channels that highlight the integral salient objects, while suppressing the other distracting ones. 3) After extracting the enhanced features, the part-whole verification (PWV) method is employed to determine whether the part and whole object features have strong agreement. Such part-whole agreements can further improve the micro-level integrity for each salient object. To demonstrate the effectiveness of our ICON, comprehensive experiments are conducted on seven challenging benchmarks. Our ICON outperforms the baseline methods in terms of a wide range of metrics. Notably, our ICON achieves about 10% relative improvement over the previous best model in terms of average false negative ratio (FNR), on six datasets. Codes and results are available at: https://github.com/mczhuge/ICON.

Pan Liao, Feng Yang, Di Wu et al.

Multi-Object Tracking (MOT) is evolving from geometric localization to Semantic MOT (SMOT) to answer complex relational queries, yet progress is hindered by semantic data scarcity and a structural disconnect between tracking architectures and Multi-modal Large Language Models (MLLMs). To address this, we introduce Grand-SMOT, a large-scale, open-world benchmark providing high-density, dual-stream narratives that comprehensively decouple individual behaviors from environmental contexts. Furthermore, we propose LLMTrack, the first framework to seamlessly integrate MLLMs into the SMOT task. LLMTrack establishes a Macro-Understanding-First paradigm, utilizing a novel Spatio-Temporal Fusion Module to align discrete geometric trajectories with continuous semantic features, effectively suppressing temporal hallucinations during online processing. Extensive experiments demonstrate that LLMTrack achieves state-of-the-art geometric tracking performance while delivering a qualitative leap in dynamic semantic reasoning. Notably, our analysis reveals that high-quality semantic narratives empower the language model to deduce complex social interactions naturally, demonstrating that direct cognitive reasoning is more effective than cumbersome explicit visual modeling. Ultimately, our contributions bridge the gap between perceptual tracking and cognitive reasoning, establishing a robust new foundation for comprehensive video understanding and intelligent narrative generation.

Hao Li, Yuanyuan Gao, Chenming Wu et al.

This paper presents GGRt, a novel approach to generalizable novel view synthesis that alleviates the need for real camera poses, complexity in processing high-resolution images, and lengthy optimization processes, thus facilitating stronger applicability of 3D Gaussian Splatting (3D-GS) in real-world scenarios. Specifically, we design a novel joint learning framework that consists of an Iterative Pose Optimization Network (IPO-Net) and a Generalizable 3D-Gaussians (G-3DG) model. With the joint learning mechanism, the proposed framework can inherently estimate robust relative pose information from the image observations and thus primarily alleviate the requirement of real camera poses. Moreover, we implement a deferred back-propagation mechanism that enables high-resolution training and inference, overcoming the resolution constraints of previous methods. To enhance the speed and efficiency, we further introduce a progressive Gaussian cache module that dynamically adjusts during training and inference. As the first pose-free generalizable 3D-GS framework, GGRt achieves inference at $\ge$ 5 FPS and real-time rendering at $\ge$ 100 FPS. Through extensive experimentation, we demonstrate that our method outperforms existing NeRF-based pose-free techniques in terms of inference speed and effectiveness. It can also approach the real pose-based 3D-GS methods. Our contributions provide a significant leap forward for the integration of computer vision and computer graphics into practical applications, offering state-of-the-art results on LLFF, KITTI, and Waymo Open datasets and enabling real-time rendering for immersive experiences.

Yuanyuan Gao, Yalun Dai, Hao Li et al.

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in scene reconstruction. However, most existing GS-based surface reconstruction methods focus on 3D objects or limited scenes. Directly applying these methods to large-scale scene reconstruction will pose challenges such as high memory costs, excessive time consumption, and lack of geometric detail, which makes it difficult to implement in practical applications. To address these issues, we propose a multi-agent collaborative fast 3DGS surface reconstruction framework based on distributed learning for large-scale surface reconstruction. Specifically, we develop local model compression (LMC) and model aggregation schemes (MAS) to achieve high-quality surface representation of large scenes while reducing GPU memory consumption. Extensive experiments on Urban3d, MegaNeRF, and BlendedMVS demonstrate that our proposed method can achieve fast and scalable high-fidelity surface reconstruction and photorealistic rendering. Our project page is available at \url{https://gyy456.github.io/CoSurfGS}.

Yuanyuan Gao, Hao Li, Jiaqi Chen et al.

Despite its significant achievements in large-scale scene reconstruction, 3D Gaussian Splatting still faces substantial challenges, including slow processing, high computational costs, and limited geometric accuracy. These core issues arise from its inherently unstructured design and the absence of efficient parallelization. To overcome these challenges simultaneously, we introduce CityGS-X, a scalable architecture built on a novel parallelized hybrid hierarchical 3D representation (PH^2-3D). As an early attempt, CityGS-X abandons the cumbersome merge-and-partition process and instead adopts a newly-designed batch-level multi-task rendering process. This architecture enables efficient multi-GPU rendering through dynamic Level-of-Detail voxel allocations, significantly improving scalability and performance. Through extensive experiments, CityGS-X consistently outperforms existing methods in terms of faster training times, larger rendering capacities, and more accurate geometric details in large-scale scenes. Notably, CityGS-X can train and render a scene with 5,000+ images in just 5 hours using only 4 * 4090 GPUs, a task that would make other alternative methods encounter Out-Of-Memory (OOM) issues and fail completely. This implies that CityGS-X is far beyond the capacity of other existing methods.

Hao Li, Yuanyuan Gao, Haosong Peng et al.

Novel-view synthesis (NVS) approaches play a critical role in vast scene reconstruction. However, these methods rely heavily on dense image inputs and prolonged training times, making them unsuitable where computational resources are limited. Additionally, few-shot methods often struggle with poor reconstruction quality in vast environments. This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes. Our approach divides the scene into regions, processed independently by drones with sparse image inputs. Using a feed-forward Gaussian model, we predict high-quality Gaussian primitives, followed by a global alignment algorithm to ensure geometric consistency. Synthetic views and depth priors are incorporated to further enhance training, while a distillation-based model aggregation mechanism enables efficient reconstruction. Our method achieves high-quality large-scale scene reconstruction and novel-view synthesis in significantly reduced training times, outperforming existing approaches in both speed and scalability. We demonstrate the effectiveness of our framework on vast aerial scenes, achieving high-quality results within minutes. Code will released on our [https://3d-aigc.github.io/DGTR].

Yansheng Li, Kun Li, Yongjun Zhang et al.

Scene graph generation (SGG) aims to understand the visual objects and their semantic relationships from one given image. Until now, lots of SGG datasets with the eyelevel view are released but the SGG dataset with the overhead view is scarcely studied. By contrast to the object occlusion problem in the eyelevel view, which impedes the SGG, the overhead view provides a new perspective that helps to promote the SGG by providing a clear perception of the spatial relationships of objects in the ground scene. To fill in the gap of the overhead view dataset, this paper constructs and releases an aerial image urban scene graph generation (AUG) dataset. Images from the AUG dataset are captured with the low-attitude overhead view. In the AUG dataset, 25,594 objects, 16,970 relationships, and 27,175 attributes are manually annotated. To avoid the local context being overwhelmed in the complex aerial urban scene, this paper proposes one new locality-preserving graph convolutional network (LPG). Different from the traditional graph convolutional network, which has the natural advantage of capturing the global context for SGG, the convolutional layer in the LPG integrates the non-destructive initial features of the objects with dynamically updated neighborhood information to preserve the local context under the premise of mining the global context. To address the problem that there exists an extra-large number of potential object relationship pairs but only a small part of them is meaningful in AUG, we propose the adaptive bounding box scaling factor for potential relationship detection (ABS-PRD) to intelligently prune the meaningless relationship pairs. Extensive experiments on the AUG dataset show that our LPG can significantly outperform the state-of-the-art methods and the effectiveness of the proposed locality-preserving strategy.

Jie Feng, Hao Huang, Junpeng Zhang et al.

Mainstreamed weakly supervised road extractors rely on highly confident pseudo-labels propagated from scribbles, and their performance often degrades gradually as the image scenes tend various. We argue that such degradation is due to the poor model's invariance to scenes with different complexities, whereas existing solutions to this problem are commonly based on crafted priors that cannot be derived from scribbles. To eliminate the reliance on such priors, we propose a novel Structure-aware Mixup and Invariance Learning framework (SA-MixNet) for weakly supervised road extraction that improves the model invariance in a data-driven manner. Specifically, we design a structure-aware Mixup scheme to paste road regions from one image onto another for creating an image scene with increased complexity while preserving the road's structural integrity. Then an invariance regularization is imposed on the predictions of constructed and origin images to minimize their conflicts, which thus forces the model to behave consistently on various scenes. Moreover, a discriminator-based regularization is designed for enhancing the connectivity meanwhile preserving the structure of roads. Combining these designs, our framework demonstrates superior performance on the DeepGlobe, Wuhan, and Massachusetts datasets outperforming the state-of-the-art techniques by 1.47%, 2.12%, 4.09% respectively in IoU metrics, and showing its potential of plug-and-play. The code will be made publicly available.

Guangyu Guo, Jiawen Yao, Yingda Xia et al.

The absence of adequately sufficient expert-level tumor annotations hinders the effectiveness of supervised learning based opportunistic cancer screening on medical imaging. Clinical reports (that are rich in descriptive textual details) can offer a "free lunch'' supervision information and provide tumor location as a type of weak label to cope with screening tasks, thus saving human labeling workloads, if properly leveraged. However, predicting cancer only using such weak labels can be very changeling since tumors are usually presented in small anatomical regions compared to the whole 3D medical scans. Weakly semi-supervised learning (WSSL) utilizes a limited set of voxel-level tumor annotations and incorporates alongside a substantial number of medical images that have only off-the-shelf clinical reports, which may strike a good balance between minimizing expert annotation workload and optimizing screening efficacy. In this paper, we propose a novel text-guided learning method to achieve highly accurate cancer detection results. Through integrating diagnostic and tumor location text prompts into the text encoder of a vision-language model (VLM), optimization of weakly supervised learning can be effectively performed in the latent space of VLM, thereby enhancing the stability of training. Our approach can leverage clinical knowledge by large-scale pre-trained VLM to enhance generalization ability, and produce reliable pseudo tumor masks to improve cancer detection. Our extensive quantitative experimental results on a large-scale cancer dataset, including 1,651 unique patients, validate that our approach can reduce human annotation efforts by at least 70% while maintaining comparable cancer detection accuracy to competing fully supervised methods (AUC value 0.961 versus 0.966).

Yuanyuan Gao, Hao Li, Yifei Liu et al.

The pursuit of spatial intelligence fundamentally relies on access to large-scale, fine-grained 3D data. However, existing approaches predominantly construct spatial understanding benchmarks by generating question-answer (QA) pairs from a limited number of manually annotated datasets, rather than systematically annotating new large-scale 3D scenes from raw web data. As a result, their scalability is severely constrained, and model performance is further hindered by domain gaps inherent in these narrowly curated datasets. In this work, we propose Holi-Spatial, the first fully automated, large-scale, spatially-aware multimodal dataset, constructed from raw video inputs without human intervention, using the proposed data curation pipeline. Holi-Spatial supports multi-level spatial supervision, ranging from geometrically accurate 3D Gaussian Splatting (3DGS) reconstructions with rendered depth maps to object-level and relational semantic annotations, together with corresponding spatial Question-Answer (QA) pairs. Following a principled and systematic pipeline, we further construct Holi-Spatial-4M, the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs spanning diverse geometric, relational, and semantic reasoning tasks. Holi-Spatial demonstrates exceptional performance in data curation quality, significantly outperforming existing feed-forward and per-scene optimized methods on datasets such as ScanNet, ScanNet++, and DL3DV. Furthermore, fine-tuning Vision-Language Models (VLMs) on spatial reasoning tasks using this dataset has also led to substantial improvements in model performance.

Lingfeng He, De Cheng, Zhiheng Ma et al.

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They typically allocate a unique sub-module for learning each task, with a task recognizer to select the appropriate sub-modules for testing images. However, due to the feature subspace misalignment from independently trained sub-modules, these methods tend to produce ambiguous decisions under misleading task-ids. To address this, we propose Cross-subspace Knowledge Alignment and Aggregation (CKAA), a novel framework that enhances model robustness against misleading task-ids through two key innovations: (1) Dual-level Knowledge Alignment (DKA): By aligning intra-class feature distributions across different subspaces and learning a robust global classifier through a feature simulation process, DKA enables the model to distinguish features from both correct and incorrect subspaces during training. (2) Task-Confidence-guided Mixture of Adapters (TC-MoA): A robust inference scheme that adaptively aggregates task-specific knowledge from relevant sub-modules based on task-confidence scores, avoiding overconfidence in misleading task-id predictions. Extensive experiments demonstrate that CKAA outperforms existing PEFT-based CL methods.