Dan Xu

Guanglei Yang, Enrico Fini, Dan Xu et al.

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely investigated in the research community and several Incremental Learning (IL) approaches have been proposed in the past years. While earlier works in computer vision have mostly focused on image classification and object detection, more recently some IL approaches for semantic segmentation have been introduced. These previous works showed that, despite its simplicity, knowledge distillation can be effectively employed to alleviate catastrophic forgetting. In this paper, we follow this research direction and, inspired by recent literature on contrastive learning, we propose a novel distillation framework, Uncertainty-aware Contrastive Distillation (\method). In a nutshell, \method~is operated by introducing a novel distillation loss that takes into account all the images in a mini-batch, enforcing similarity between features associated to all the pixels from the same classes, and pulling apart those corresponding to pixels from different classes. In order to mitigate catastrophic forgetting, we contrast features of the new model with features extracted by a frozen model learned at the previous incremental step. Our experimental results demonstrate the advantage of the proposed distillation technique, which can be used in synergy with previous IL approaches, and leads to state-of-art performance on three commonly adopted benchmarks for incremental semantic segmentation. The code is available at \url{https://github.com/ygjwd12345/UCD}.

Hanrong Ye, Dan Xu

Multi-task dense scene understanding is a thriving research domain that requires simultaneous perception and reasoning on a series of correlated tasks with pixel-wise prediction. Most existing works encounter a severe limitation of modeling in the locality due to heavy utilization of convolution operations, while learning interactions and inference in a global spatial-position and multi-task context is critical for this problem. In this paper, we propose a novel end-to-end Inverted Pyramid multi-task Transformer (InvPT) to perform simultaneous modeling of spatial positions and multiple tasks in a unified framework. To the best of our knowledge, this is the first work that explores designing a transformer structure for multi-task dense prediction for scene understanding. Besides, it is widely demonstrated that a higher spatial resolution is remarkably beneficial for dense predictions, while it is very challenging for existing transformers to go deeper with higher resolutions due to huge complexity to large spatial size. InvPT presents an efficient UP-Transformer block to learn multi-task feature interaction at gradually increased resolutions, which also incorporates effective self-attention message passing and multi-scale feature aggregation to produce task-specific prediction at a high resolution. Our method achieves superior multi-task performance on NYUD-v2 and PASCAL-Context datasets respectively, and significantly outperforms previous state-of-the-arts. The code is available at https://github.com/prismformore/InvPT

Fa-Ting Hong, Dan Xu

Talking head video generation aims to animate a human face in a still image with dynamic poses and expressions using motion information derived from a target-driving video, while maintaining the person's identity in the source image. However, dramatic and complex motions in the driving video cause ambiguous generation, because the still source image cannot provide sufficient appearance information for occluded regions or delicate expression variations, which produces severe artifacts and significantly degrades the generation quality. To tackle this problem, we propose to learn a global facial representation space, and design a novel implicit identity representation conditioned memory compensation network, coined as MCNet, for high-fidelity talking head generation.~Specifically, we devise a network module to learn a unified spatial facial meta-memory bank from all training samples, which can provide rich facial structure and appearance priors to compensate warped source facial features for the generation. Furthermore, we propose an effective query mechanism based on implicit identity representations learned from the discrete keypoints of the source image. It can greatly facilitate the retrieval of more correlated information from the memory bank for the compensation. Extensive experiments demonstrate that MCNet can learn representative and complementary facial memory, and can clearly outperform previous state-of-the-art talking head generation methods on VoxCeleb1 and CelebV datasets. Please check our \href{https://github.com/harlanhong/ICCV2023-MCNET}{Project}.

Yanan Liu, Anqi Zhu, Jingmin Zhu et al.

Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled exemplar is available for each novel action. A key challenge is learning representations that capture the hierarchical and compositional structure of human motion while aligning effectively with high-level action semantics under extreme data scarcity. Existing approaches, largely based on Euclidean embeddings and low-level motion cues, struggle to model the tree-like organization of skeleton data, limiting cross-modal alignment and generalization to unseen action categories. We propose SkelHCC, a unified skeleton hyperbolic CLIP-driven cache adaptation framework for one-shot skeleton-based action recognition. SkelHCC introduces an Explicitly Hierarchical Hyperbolic CLIP (EH-HCLIP) module that embeds skeleton sequences and action language into a shared hyperbolic space. By leveraging the negative curvature and exponential volume growth of hyperbolic geometry, EH-HCLIP naturally encodes the joint-part-body hierarchy of human anatomy and yields structurally consistent cross-modal representations. To support efficient one-shot adaptation, SkelHCC further integrates a training-free LLM-guided Multi-granularity Voting Cache (LMV-Cache) for context-aware inference. Experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD demonstrate that SkelHCC consistently outperforms state-of-the-art methods.

Lian Xu, Wanli Ouyang, Mohammed Bennamoun et al.

This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer model can also effectively capture class-specific attention for more discriminative object localization by learning multiple class tokens within the transformer. To this end, we propose a Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens. The proposed MCTformer can successfully produce class-discriminative object localization maps from class-to-patch attentions corresponding to different class tokens. We also propose to use a patch-level pairwise affinity, which is extracted from the patch-to-patch transformer attention, to further refine the localization maps. Moreover, the proposed framework is shown to fully complement the Class Activation Mapping (CAM) method, leading to remarkably superior WSSS results on the PASCAL VOC and MS COCO datasets. These results underline the importance of the class token for WSSS.

Lewei Yao, Jianhua Han, Youpeng Wen et al.

Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all category names of detection datasets into sentences, which leads to inefficient interaction between category names. This paper presents DetCLIP, a paralleled visual-concept pre-training method for open-world detection by resorting to knowledge enrichment from a designed concept dictionary. To achieve better learning efficiency, we propose a novel paralleled concept formulation that extracts concepts separately to better utilize heterogeneous datasets (i.e., detection, grounding, and image-text pairs) for training. We further design a concept dictionary~(with descriptions) from various online sources and detection datasets to provide prior knowledge for each concept. By enriching the concepts with their descriptions, we explicitly build the relationships among various concepts to facilitate the open-domain learning. The proposed concept dictionary is further used to provide sufficient negative concepts for the construction of the word-region alignment loss\, and to complete labels for objects with missing descriptions in captions of image-text pair data. The proposed framework demonstrates strong zero-shot detection performances, e.g., on the LVIS dataset, our DetCLIP-T outperforms GLIP-T by 9.9% mAP and obtains a 13.5% improvement on rare categories compared to the fully-supervised model with the same backbone as ours.

Lian Xu, Mohammed Bennamoun, Farid Boussaid et al.

This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localization maps as pseudo labels. Building upon the observation that the attended regions of the one-class token in the standard vision transformer can contribute to a class-agnostic localization map, we explore the potential of the transformer model to capture class-specific attention for class-discriminative object localization by learning multiple class tokens. We introduce a Multi-Class Token transformer, which incorporates multiple class tokens to enable class-aware interactions with the patch tokens. To achieve this, we devise a class-aware training strategy that establishes a one-to-one correspondence between the output class tokens and the ground-truth class labels. Moreover, a Contrastive-Class-Token (CCT) module is proposed to enhance the learning of discriminative class tokens, enabling the model to better capture the unique characteristics and properties of each class. As a result, class-discriminative object localization maps can be effectively generated by leveraging the class-to-patch attentions associated with different class tokens. To further refine these localization maps, we propose the utilization of patch-level pairwise affinity derived from the patch-to-patch transformer attention. Furthermore, the proposed framework seamlessly complements the Class Activation Mapping (CAM) method, resulting in significantly improved WSSS performance on the PASCAL VOC 2012 and MS COCO 2014 datasets. These results underline the importance of the class token for WSSS.

Lewei Yao, Jianhua Han, Xiaodan Liang et al.

This paper presents DetCLIPv2, an efficient and scalable training framework that incorporates large-scale image-text pairs to achieve open-vocabulary object detection (OVD). Unlike previous OVD frameworks that typically rely on a pre-trained vision-language model (e.g., CLIP) or exploit image-text pairs via a pseudo labeling process, DetCLIPv2 directly learns the fine-grained word-region alignment from massive image-text pairs in an end-to-end manner. To accomplish this, we employ a maximum word-region similarity between region proposals and textual words to guide the contrastive objective. To enable the model to gain localization capability while learning broad concepts, DetCLIPv2 is trained with a hybrid supervision from detection, grounding and image-text pair data under a unified data formulation. By jointly training with an alternating scheme and adopting low-resolution input for image-text pairs, DetCLIPv2 exploits image-text pair data efficiently and effectively: DetCLIPv2 utilizes 13X more image-text pairs than DetCLIP with a similar training time and improves performance. With 13M image-text pairs for pre-training, DetCLIPv2 demonstrates superior open-vocabulary detection performance, e.g., DetCLIPv2 with Swin-T backbone achieves 40.4% zero-shot AP on the LVIS benchmark, which outperforms previous works GLIP/GLIPv2/DetCLIP by 14.4/11.4/4.5% AP, respectively, and even beats its fully-supervised counterpart by a large margin.

Fa-Ting Hong, Longhao Zhang, Li Shen et al.

Talking head video generation aims to produce a synthetic human face video that contains the identity and pose information respectively from a given source image and a driving video.Existing works for this task heavily rely on 2D representations (e.g. appearance and motion) learned from the input images. However, dense 3D facial geometry (e.g. pixel-wise depth) is extremely important for this task as it is particularly beneficial for us to essentially generate accurate 3D face structures and distinguish noisy information from the possibly cluttered background. Nevertheless, dense 3D geometry annotations are prohibitively costly for videos and are typically not available for this video generation task. In this paper, we first introduce a self-supervised geometry learning method to automatically recover the dense 3D geometry (i.e.depth) from the face videos without the requirement of any expensive 3D annotation data. Based on the learned dense depth maps, we further propose to leverage them to estimate sparse facial keypoints that capture the critical movement of the human head. In a more dense way, the depth is also utilized to learn 3D-aware cross-modal (i.e. appearance and depth) attention to guide the generation of motion fields for warping source image representations. All these contributions compose a novel depth-aware generative adversarial network (DaGAN) for talking head generation. Extensive experiments conducted demonstrate that our proposed method can generate highly realistic faces, and achieve significant results on the unseen human faces.

Hanrong Ye, Dan Xu

Learning discriminative task-specific features simultaneously for multiple distinct tasks is a fundamental problem in multi-task learning. Recent state-of-the-art models consider directly decoding task-specific features from one shared task-generic feature (e.g., feature from a backbone layer), and utilize carefully designed decoders to produce multi-task features. However, as the input feature is fully shared and each task decoder also shares decoding parameters for different input samples, it leads to a static feature decoding process, producing less discriminative task-specific representations. To tackle this limitation, we propose TaskExpert, a novel multi-task mixture-of-experts model that enables learning multiple representative task-generic feature spaces and decoding task-specific features in a dynamic manner. Specifically, TaskExpert introduces a set of expert networks to decompose the backbone feature into several representative task-generic features. Then, the task-specific features are decoded by using dynamic task-specific gating networks operating on the decomposed task-generic features. Furthermore, to establish long-range modeling of the task-specific representations from different layers of TaskExpert, we design a multi-task feature memory that updates at each layer and acts as an additional feature expert for dynamic task-specific feature decoding. Extensive experiments demonstrate that our TaskExpert clearly outperforms previous best-performing methods on all 9 metrics of two competitive multi-task learning benchmarks for visual scene understanding (i.e., PASCAL-Context and NYUD-v2). Codes and models will be made publicly available at https://github.com/prismformore/Multi-Task-Transformer

Yuzhang Shang, Dan Xu, Bin Duan et al.

Relying on the premise that the performance of a binary neural network can be largely restored with eliminated quantization error between full-precision weight vectors and their corresponding binary vectors, existing works of network binarization frequently adopt the idea of model robustness to reach the aforementioned objective. However, robustness remains to be an ill-defined concept without solid theoretical support. In this work, we introduce the Lipschitz continuity, a well-defined functional property, as the rigorous criteria to define the model robustness for BNN. We then propose to retain the Lipschitz continuity as a regularization term to improve the model robustness. Particularly, while the popular Lipschitz-involved regularization methods often collapse in BNN due to its extreme sparsity, we design the Retention Matrices to approximate spectral norms of the targeted weight matrices, which can be deployed as the approximation for the Lipschitz constant of BNNs without the exact Lipschitz constant computation (NP-hard). Our experiments prove that our BNN-specific regularization method can effectively strengthen the robustness of BNN (testified on ImageNet-C), achieving state-of-the-art performance on CIFAR and ImageNet.

Yuzhang Shang, Dan Xu, Ziliang Zong et al.

Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit. However, there is still a huge performance gap between Binary Neural Networks (BNNs) and their full-precision (FP) counterparts. As the quantization error caused by weights binarization has been reduced in earlier works, the activations binarization becomes the major obstacle for further improvement of the accuracy. BNN characterises a unique and interesting structure, where the binary and latent FP activations exist in the same forward pass (i.e., $\text{Binarize}(\mathbf{a}_F) = \mathbf{a}_B$). To mitigate the information degradation caused by the binarization operation from FP to binary activations, we establish a novel contrastive learning framework while training BNNs through the lens of Mutual Information (MI) maximization. MI is introduced as the metric to measure the information shared between binary and FP activations, which assists binarization with contrastive learning. Specifically, the representation ability of the BNNs is greatly strengthened via pulling the positive pairs with binary and FP activations from the same input samples, as well as pushing negative pairs from different samples (the number of negative pairs can be exponentially large). This benefits the downstream tasks, not only classification but also segmentation and depth estimation, etc. The experimental results show that our method can be implemented as a pile-up module on existing state-of-the-art binarization methods and can remarkably improve the performance over them on CIFAR-10/100 and ImageNet, in addition to the great generalization ability on NYUD-v2.

Chi Yan, Delin Qu, Dan Xu et al.

In this paper, we introduce \textbf{GS-SLAM} that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better balance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Specifically, we propose an adaptive expansion strategy that adds new or deletes noisy 3D Gaussians in order to efficiently reconstruct new observed scene geometry and improve the mapping of previously observed areas. This strategy is essential to extend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing methods. Moreover, in the pose tracking process, an effective coarse-to-fine technique is designed to select reliable 3D Gaussian representations to optimize camera pose, resulting in runtime reduction and robust estimation. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets. Project page: https://gs-slam.github.io/.

Ping Liu, Qianqi Shen, Jianqiang Shen et al.

Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components. While individually optimizable, this fragmented architecture incurs high maintenance overhead and results in inconsistent behaviors, particularly for long-tail queries. In this work, we propose and deploy a unified structured query understanding system that consolidates these heterogeneous functions into a single Small Language Model (SLM) that performs schema-constrained generation. To address the data bottlenecks inherent in unified modeling, we introduce Query Illuminator, a dual-purpose framework serving as: (i) a teacher model for high-quality auto-annotation and distillation, and (ii) a surrogate judge for scalable evaluation where human labels are scarce. We validate this approach through extensive offline and online tests within LinkedIn's Job Search system. Furthermore, we demonstrate the framework's horizontal extensibility through a cross-domain case study on People Search. The results show improved user engagement and reduced operational costs, achieved while satisfying strict low-latency serving constraints on limited GPU resources.

Yuxin Wang, Wayne Wu, Dan Xu

Implicit neural representations have shown powerful capacity in modeling real-world 3D scenes, offering superior performance in novel view synthesis. In this paper, we target a more challenging scenario, i.e., joint scene novel view synthesis and editing based on implicit neural scene representations. State-of-the-art methods in this direction typically consider building separate networks for these two tasks (i.e., view synthesis and editing). Thus, the modeling of interactions and correlations between these two tasks is very limited, which, however, is critical for learning high-quality scene representations. To tackle this problem, in this paper, we propose a unified Neural Radiance Field (NeRF) framework to effectively perform joint scene decomposition and composition for modeling real-world scenes. The decomposition aims at learning disentangled 3D representations of different objects and the background, allowing for scene editing, while scene composition models an entire scene representation for novel view synthesis. Specifically, with a two-stage NeRF framework, we learn a coarse stage for predicting a global radiance field as guidance for point sampling, and in the second fine-grained stage, we perform scene decomposition by a novel one-hot object radiance field regularization module and a pseudo supervision via inpainting to handle ambiguous background regions occluded by objects. The decomposed object-level radiance fields are further composed by using activations from the decomposition module. Extensive quantitative and qualitative results show the effectiveness of our method for scene decomposition and composition, outperforming state-of-the-art methods for both novel-view synthesis and editing tasks.

Jaehyeok Kim, Dongyoon Wee, Dan Xu

We introduce You Only Train Once (YOTO), a dynamic human generation framework, which performs free-viewpoint rendering of different human identities with distinct motions, via only one-time training from monocular videos. Most prior works for the task require individualized optimization for each input video that contains a distinct human identity, leading to a significant amount of time and resources for the deployment, thereby impeding the scalability and the overall application potential of the system. In this paper, we tackle this problem by proposing a set of learnable identity codes to expand the capability of the framework for multi-identity free-viewpoint rendering, and an effective pose-conditioned code query mechanism to finely model the pose-dependent non-rigid motions. YOTO optimizes neural radiance fields (NeRF) by utilizing designed identity codes to condition the model for learning various canonical T-pose appearances in a single shared volumetric representation. Besides, our joint learning of multiple identities within a unified model incidentally enables flexible motion transfer in high-quality photo-realistic renderings for all learned appearances. This capability expands its potential use in important applications, including Virtual Reality. We present extensive experimental results on ZJU-MoCap and PeopleSnapshot to clearly demonstrate the effectiveness of our proposed model. YOTO shows state-of-the-art performance on all evaluation metrics while showing significant benefits in training and inference efficiency as well as rendering quality. The code and model will be made publicly available soon.

Yiwen Tang, Zoey Guo, Kaixin Zhu et al.

Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generation recently. However, applying RL to 3D generation remains largely unexplored due to the higher spatial complexity of 3D objects, which require globally consistent geometry and fine-grained local textures. This makes 3D generation significantly sensitive to reward designs and RL algorithms. To address these challenges, we conduct the first systematic study of RL for text-to-3D autoregressive generation across several dimensions. (1) Reward designs: We evaluate reward dimensions and model choices, showing that alignment with human preference is crucial, and that general multi-modal models provide robust signal for 3D attributes. (2) RL algorithms: We study GRPO variants, highlighting the effectiveness of token-level optimization, and further investigate the scaling of training data and iterations. (3) Text-to-3D Benchmarks: Since existing benchmarks fail to measure implicit reasoning abilities in 3D generation models, we introduce MME-3DR. (4) Advanced RL paradigms: Motivated by the natural hierarchy of 3D generation, we propose Hi-GRPO, which optimizes the global-to-local hierarchical 3D generation through dedicated reward ensembles. Based on these insights, we develop AR3D-R1, the first RL-enhanced text-to-3D model, expert from coarse shape to texture refinement. We hope this study provides insights into RL-driven reasoning for 3D generation. Code is released at https://github.com/Ivan-Tang-3D/3DGen-R1.

Delin Qu, Chi Yan, Dong Wang et al.

Implicit neural SLAM has achieved remarkable progress recently. Nevertheless, existing methods face significant challenges in non-ideal scenarios, such as motion blur or lighting variation, which often leads to issues like convergence failures, localization drifts, and distorted mapping. To address these challenges, we propose EN-SLAM, the first event-RGBD implicit neural SLAM framework, which effectively leverages the high rate and high dynamic range advantages of event data for tracking and mapping. Specifically, EN-SLAM proposes a differentiable CRF (Camera Response Function) rendering technique to generate distinct RGB and event camera data via a shared radiance field, which is optimized by learning a unified implicit representation with the captured event and RGBD supervision. Moreover, based on the temporal difference property of events, we propose a temporal aggregating optimization strategy for the event joint tracking and global bundle adjustment, capitalizing on the consecutive difference constraints of events, significantly enhancing tracking accuracy and robustness. Finally, we construct the simulated dataset DEV-Indoors and real captured dataset DEV-Reals containing 6 scenes, 17 sequences with practical motion blur and lighting changes for evaluations. Experimental results show that our method outperforms the SOTA methods in both tracking ATE and mapping ACC with a real-time 17 FPS in various challenging environments. Project page: https://delinqu.github.io/EN-SLAM.

Hanrong Ye, Jason Kuen, Qing Liu et al.

We propose SegGen, a highly-effective training data generation method for image segmentation, which pushes the performance limits of state-of-the-art segmentation models to a significant extent. SegGen designs and integrates two data generation strategies: MaskSyn and ImgSyn. (i) MaskSyn synthesizes new mask-image pairs via our proposed text-to-mask generation model and mask-to-image generation model, greatly improving the diversity in segmentation masks for model supervision; (ii) ImgSyn synthesizes new images based on existing masks using the mask-to-image generation model, strongly improving image diversity for model inputs. On the highly competitive ADE20K and COCO benchmarks, our data generation method markedly improves the performance of state-of-the-art segmentation models in semantic segmentation, panoptic segmentation, and instance segmentation. Notably, in terms of the ADE20K mIoU, Mask2Former R50 is largely boosted from 47.2 to 49.9 (+2.7); Mask2Former Swin-L is also significantly increased from 56.1 to 57.4 (+1.3). These promising results strongly suggest the effectiveness of our SegGen even when abundant human-annotated training data is utilized. Moreover, training with our synthetic data makes the segmentation models more robust towards unseen domains. Project website: https://seggenerator.github.io

Yang Cao, Yihan Zeng, Hang Xu et al.

Open-vocabulary 3D Object Detection (OV-3DDet) aims to detect objects from an arbitrary list of categories within a 3D scene, which remains seldom explored in the literature. There are primarily two fundamental problems in OV-3DDet, i.e., localizing and classifying novel objects. This paper aims at addressing the two problems simultaneously via a unified framework, under the condition of limited base categories. To localize novel 3D objects, we propose an effective 3D Novel Object Discovery strategy, which utilizes both the 3D box geometry priors and 2D semantic open-vocabulary priors to generate pseudo box labels of the novel objects. To classify novel object boxes, we further develop a cross-modal alignment module based on discovered novel boxes, to align feature spaces between 3D point cloud and image/text modalities. Specifically, the alignment process contains a class-agnostic and a class-discriminative alignment, incorporating not only the base objects with annotations but also the increasingly discovered novel objects, resulting in an iteratively enhanced alignment. The novel box discovery and crossmodal alignment are jointly learned to collaboratively benefit each other. The novel object discovery can directly impact the cross-modal alignment, while a better feature alignment can, in turn, boost the localization capability, leading to a unified OV-3DDet framework, named CoDA, for simultaneous novel object localization and classification. Extensive experiments on two challenging datasets (i.e., SUN-RGBD and ScanNet) demonstrate the effectiveness of our method and also show a significant mAP improvement upon the best-performing alternative method by 80%. Codes and pre-trained models are released on the project page.

Hanrong Ye, Dan Xu

Multi-task scene understanding aims to design models that can simultaneously predict several scene understanding tasks with one versatile model. Previous studies typically process multi-task features in a more local way, and thus cannot effectively learn spatially global and cross-task interactions, which hampers the models' ability to fully leverage the consistency of various tasks in multi-task learning. To tackle this problem, we propose an Inverted Pyramid multi-task Transformer, capable of modeling cross-task interaction among spatial features of different tasks in a global context. Specifically, we first utilize a transformer encoder to capture task-generic features for all tasks. And then, we design a transformer decoder to establish spatial and cross-task interaction globally, and a novel UP-Transformer block is devised to increase the resolutions of multi-task features gradually and establish cross-task interaction at different scales. Furthermore, two types of Cross-Scale Self-Attention modules, i.e., Fusion Attention and Selective Attention, are proposed to efficiently facilitate cross-task interaction across different feature scales. An Encoder Feature Aggregation strategy is further introduced to better model multi-scale information in the decoder. Comprehensive experiments on several 2D/3D multi-task benchmarks clearly demonstrate our proposal's effectiveness, establishing significant state-of-the-art performances.

Jiebao Zhang, Wenhua Qian, Rencan Nie et al.

Deep neural networks are vulnerable to adversarial attacks. Most $L_{0}$-norm based white-box attacks craft perturbations by the gradient of models to the input. Since the computation cost and memory limitation of calculating the Hessian matrix, the application of Hessian or approximate Hessian in white-box attacks is gradually shelved. In this work, we note that the sparsity requirement on perturbations naturally lends itself to the usage of Hessian information. We study the attack performance and computation cost of the attack method based on the Hessian with a limited number of perturbation pixels. Specifically, we propose the Limited Pixel BFGS (LP-BFGS) attack method by incorporating the perturbation pixel selection strategy and the BFGS algorithm. Pixels with top-k attribution scores calculated by the Integrated Gradient method are regarded as optimization variables of the LP-BFGS attack. Experimental results across different networks and datasets demonstrate that our approach has comparable attack ability with reasonable computation in different numbers of perturbation pixels compared with existing solutions.

Siwei Yang, Hanrong Ye, Dan Xu

This paper targets the problem of multi-task dense prediction which aims to achieve simultaneous learning and inference on a bunch of multiple dense prediction tasks in a single framework. A core objective in design is how to effectively model cross-task interactions to achieve a comprehensive improvement on different tasks based on their inherent complementarity and consistency. Existing works typically design extra expensive distillation modules to perform explicit interaction computations among different task-specific features in both training and inference, bringing difficulty in adaptation for different task sets, and reducing efficiency due to clearly increased size of multi-task models. In contrast, we introduce feature-wise contrastive consistency into modeling the cross-task interactions for multi-task dense prediction. We propose a novel multi-task contrastive regularization method based on the consistency to effectively boost the representation learning of the different sub-tasks, which can also be easily generalized to different multi-task dense prediction frameworks, and costs no additional computation in the inference. Extensive experiments on two challenging datasets (i.e. NYUD-v2 and Pascal-Context) clearly demonstrate the superiority of the proposed multi-task contrastive learning approach for dense predictions, establishing new state-of-the-art performances.

Xiaodong Mei, Diankun Zhang, Hongwei Xie et al.

Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene understanding and reasoning capabilities. Recent attempts to incorporate dense visual supervision via world modeling often overemphasize pixel-level image reconstruction, neglecting semantically meaningful scene representation learning. In this work, we propose LVDrive, a Latent Visual representation enhanced VLA framework for autonomous driving. LVDrive introduces a future scene prediction task into the VLA paradigm, where future representations are learned entirely in a high-level latent space under auxiliary supervision from a pretrained vision backbone. Departing from inefficient autoregressive generation, we jointly model future scene and motion prediction within a unified embedding space, processed in a single forward pass to conduct the future-aware reasoning. We further design a two-stage trajectory decoding strategy that explicitly leverages the learned latent future representations to refine trajectory generation. Extensive experiments on the challenging Bench2Drive benchmark demonstrate that LVDrive achieves significant improvements in closed-loop driving performance, outperforming both action supervised methods and image-reconstruction-based world model approaches.

Yanan Liu, Qinya Li, Hao Zhang et al.

Reconstructing 4D (3D+t) cardiac geometry from sparse 2D echocardiography is highly desirable yet fundamentally challenged by geometric ambiguity and temporal discontinuity. To tackle these issues, we propose Echo4DIR, a novel test-time 4D implicit reconstruction framework. Specifically, we learn robust 3D shape priors from statistical shape models (SSMs) via a cardiac conditional SDF, constructing an Epipolar Mask Encoder module with epipolar cross attention to effectively fuse multi-view features. To bridge the synthetic-to-real domain gap, we introduce a self-supervised SDF-tailored differentiable rendering strategy for patient-specific 3D shape adaptation using uncalibrated clinical masks without requiring 3D ground truth. Crucially, the inherent continuity of implicit representation overcomes sparse observations, enabling anatomically reliable geometry at arbitrary resolutions. Furthermore, to empower our framework with physically continuous 4D extension, we introduce a Radial SDF Alignment strategy that strictly locks shape evolution to the predicted velocity field, fundamentally eliminating mesh drift. Extensive experiments on synthetic benchmarks and real clinical datasets demonstrate that Echo4DIR achieves state-of-the-art 4D cardiac mesh reconstruction, notably yielding an impressive clinical overlap of up to 98.35% Dice and 96.75% IoU.

Hongzhi Ruan, Pei Liu, Weiliang Ma et al.

Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promising direction. However, naively incorporating all available synthetic data is inefficient and leads to distribution shifts, and optimizing data mixture under practical training budgets remains a critical yet under-explored problem. In this sense, we claim that the mixture of training data requires clear guidance in terms of scene types and quantities. Particularly in this work, we conceptualize the data mixture approximately as a dynamic optimization process that iteratively adjusts the training data mixture to maximize model performance, guided by closed-loop evaluation feedback, and propose AutoScale, a fully automated closed-loop data engine unifying scene representation, data mixture optimization and retrieval, as well as model training and evaluation. Specifically, we propose Graph Regularized AutoEncoder (Graph-RAE) for driving scene representations, introduce Cluster-aware Gradient Ascent (Cluster-GA) for cluster-wise importance estimation and reweighting, and perform cluster-guided vector retrieval to select high-value samples. Experiments on NavSim demonstrate that AutoScale outperforms vanilla co-training and cross-domain baselines, achieving better performance with fewer synthetic samples under constrained budgets.

You Zhang, Jin Wang, Liang-Chih Yu et al.

Effectively and efficiently adapting a pre-trained language model (PLM) for human-centered text understanding (HCTU) is challenging since user tokens are million-level in most personalized applications and do not have concrete explicit semantics. A standard and parameter-efficient approach (e.g., LoRA) necessitates memorizing numerous suits of adapters for each user. In this work, we introduce a personalized LoRA (PLoRA) with a plug-and-play (PnP) framework for the HCTU task. PLoRA is effective, parameter-efficient, and dynamically deploying in PLMs. Moreover, a personalized dropout and a mutual information maximizing strategies are adopted and hence the proposed PLoRA can be well adapted to few/zero-shot learning scenarios for the cold-start issue. Experiments conducted on four benchmark datasets show that the proposed method outperforms existing methods in full/few/zero-shot learning scenarios for the HCTU task, even though it has fewer trainable parameters. For reproducibility, the code for this paper is available at: https://github.com/yoyo-yun/PLoRA.

Jiebao Zhang, Wenhua Qian, Rencan Nie et al.

A counter-intuitive property of convolutional neural networks (CNNs) is their inherent susceptibility to adversarial examples, which severely hinders the application of CNNs in security-critical fields. Adversarial examples are similar to original examples but contain malicious perturbations. Adversarial training is a simple and effective defense method to improve the robustness of CNNs to adversarial examples. The mechanisms behind adversarial examples and adversarial training are worth exploring. Therefore, this work investigates similarities and differences between normally trained CNNs (NT-CNNs) and adversarially trained CNNs (AT-CNNs) in information extraction from the mutual information perspective. We show that 1) whether NT-CNNs or AT-CNNs, for original and adversarial examples, the trends towards mutual information are almost similar throughout training; 2) compared with normal training, adversarial training is more difficult and the amount of information that AT-CNNs extract from the input is less; 3) the CNNs trained with different methods have different preferences for certain types of information; NT-CNNs tend to extract texture-based information from the input, while AT-CNNs prefer to shape-based information. The reason why adversarial examples mislead CNNs may be that they contain more texture-based information about other classes. Furthermore, we also analyze the mutual information estimators used in this work and find that they outline the geometric properties of the middle layer's output.

Fa-Ting Hong, Yunfei Liu, Yu Li et al.

Audio-driven talking head synthesis strives to generate lifelike video portraits from provided audio. The diffusion model, recognized for its superior quality and robust generalization, has been explored for this task. However, establishing a robust correspondence between temporal audio cues and corresponding spatial facial expressions with diffusion models remains a significant challenge in talking head generation. To bridge this gap, we present DreamHead, a hierarchical diffusion framework that learns spatial-temporal correspondences in talking head synthesis without compromising the model's intrinsic quality and adaptability.~DreamHead learns to predict dense facial landmarks from audios as intermediate signals to model the spatial and temporal correspondences.~Specifically, a first hierarchy of audio-to-landmark diffusion is first designed to predict temporally smooth and accurate landmark sequences given audio sequence signals. Then, a second hierarchy of landmark-to-image diffusion is further proposed to produce spatially consistent facial portrait videos, by modeling spatial correspondences between the dense facial landmark and appearance. Extensive experiments show that proposed DreamHead can effectively learn spatial-temporal consistency with the designed hierarchical diffusion and produce high-fidelity audio-driven talking head videos for multiple identities.

Jaehyeok Kim, Dongyoon Wee, Dan Xu

This paper introduces Motion-oriented Compositional Neural Radiance Fields (MoCo-NeRF), a framework designed to perform free-viewpoint rendering of monocular human videos via novel non-rigid motion modeling approach. In the context of dynamic clothed humans, complex cloth dynamics generate non-rigid motions that are intrinsically distinct from skeletal articulations and critically important for the rendering quality. The conventional approach models non-rigid motions as spatial (3D) deviations in addition to skeletal transformations. However, it is either time-consuming or challenging to achieve optimal quality due to its high learning complexity without a direct supervision. To target this problem, we propose a novel approach of modeling non-rigid motions as radiance residual fields to benefit from more direct color supervision in the rendering and utilize the rigid radiance fields as a prior to reduce the complexity of the learning process. Our approach utilizes a single multiresolution hash encoding (MHE) to concurrently learn the canonical T-pose representation from rigid skeletal motions and the radiance residual field for non-rigid motions. Additionally, to further improve both training efficiency and usability, we extend MoCo-NeRF to support simultaneous training of multiple subjects within a single framework, thanks to our effective design for modeling non-rigid motions. This scalability is achieved through the integration of a global MHE and learnable identity codes in addition to multiple local MHEs. We present extensive results on ZJU-MoCap and MonoCap, clearly demonstrating state-of-the-art performance in both single- and multi-subject settings. The code and model will be made publicly available at the project page: https://stevejaehyeok.github.io/publications/moco-nerf.

Hanrong Ye, Dan Xu

Recently, there has been an increased interest in the practical problem of learning multiple dense scene understanding tasks from partially annotated data, where each training sample is only labeled for a subset of the tasks. The missing of task labels in training leads to low-quality and noisy predictions, as can be observed from state-of-the-art methods. To tackle this issue, we reformulate the partially-labeled multi-task dense prediction as a pixel-level denoising problem, and propose a novel multi-task denoising diffusion framework coined as DiffusionMTL. It designs a joint diffusion and denoising paradigm to model a potential noisy distribution in the task prediction or feature maps and generate rectified outputs for different tasks. To exploit multi-task consistency in denoising, we further introduce a Multi-Task Conditioning strategy, which can implicitly utilize the complementary nature of the tasks to help learn the unlabeled tasks, leading to an improvement in the denoising performance of the different tasks. Extensive quantitative and qualitative experiments demonstrate that the proposed multi-task denoising diffusion model can significantly improve multi-task prediction maps, and outperform the state-of-the-art methods on three challenging multi-task benchmarks, under two different partial-labeling evaluation settings. The code is available at https://prismformore.github.io/diffusionmtl/.

Yang Cao, Feize Wu, Dave Zhenyu Chen et al.

Current multi-view indoor 3D object detectors rely on sensor geometry that is costly to obtain (i.e., precisely calibrated multi-view camera poses) to fuse multi-view information into a global scene representation, limiting deployment in real-world scenes. We target a more practical setting: Sensor-Geometry-Free (SG-Free) multi-view indoor 3D object detection, where there are no sensor-provided geometric inputs (multi-view poses or depth). Recent Visual Geometry Grounded Transformer (VGGT) shows that strong 3D cues can be inferred directly from images. Building on this insight, we present VGGT-Det, the first framework tailored for SG-Free multi-view indoor 3D object detection. Rather than merely consuming VGGT predictions, our method integrates VGGT encoder into a transformer-based pipeline. To effectively leverage both the semantic and geometric priors from inside VGGT, we introduce two novel key components: (i) Attention-Guided Query Generation (AG): exploits VGGT attention maps as semantic priors to initialize object queries, improving localization by focusing on object regions while preserving global spatial structure; (ii) Query-Driven Feature Aggregation (QD): a learnable See-Query interacts with object queries to 'see' what they need, and then dynamically aggregates multi-level geometric features across VGGT layers that progressively lift 2D features into 3D. Experiments show that VGGT-Det significantly surpasses the best-performing method in the SG-Free setting by 4.4 and 8.6 mAP@0.25 on ScanNet and ARKitScenes, respectively. Ablation study shows that VGGT's internally learned semantic and geometric priors can be effectively leveraged by our AG and QD.

Ren Kai Tan, Chao Qian, Dan Xu et al.

Topology Optimization (TO) provides a systematic approach for obtaining structure design with optimum performance of interest. However, the process requires numerical evaluation of objective function and constraints at each iteration, which is computational expensive especially for large-scale design. Deep learning-based models have been developed to accelerate the process either by acting as surrogate models replacing the simulation process, or completely replacing the optimization process. However, most of them require a large set of labelled training data, which are generated mostly through simulations. The data generation time scales rapidly with the design domain size, decreasing the efficiency of the method itself. Another major issue is the weak generalizability of most deep learning models. Most models are trained to work with the design problem similar to that used for data generation and require retraining if the design problem changes. In this work a scalable deep learning-based model-order-reduction method is proposed to accelerate large-scale TO process, by utilizing MapNet, a neural network which maps the field of interest from coarse-scale to fine-scale. The proposed method allows for each simulation of the TO process to be performed at a coarser mesh, thereby greatly reducing the total computational time. Moreover, by using domain fragmentation, the transferability of the MapNet is largely improved. Specifically, it has been demonstrated that the MapNet trained using data from one cantilever beam design with a specific loading condition can be directly applied to other structure design problems with different domain shapes, sizes, boundary and loading conditions.

Fa-Ting Hong, Dan Xu

One-shot talking head video generation uses a source image and driving video to create a synthetic video where the source person's facial movements imitate those of the driving video. However, differences in scale between the source and driving images remain a challenge for face reenactment. Existing methods attempt to locate a frame in the driving video that aligns best with the source image, but imprecise alignment can result in suboptimal outcomes. To this end, we introduce a scale transformation module that can automatically adjust the scale of the driving image to fit that of the source image, by using the information of scale difference maintained in the detected keypoints of the source image and the driving frame. Furthermore, to keep perceiving the scale information of faces during the generation process, we incorporate the scale information learned from the scale transformation module into each layer of the generation process to produce a final result with an accurate scale. Our method can perform accurate motion transfer between the two images without any anchor frame, achieved through the contributions of the proposed online scale transformation facial reenactment network. Extensive experiments have demonstrated that our proposed method adjusts the scale of the driving face automatically according to the source face, and generates high-quality faces with an accurate scale in the cross-identity facial reenactment.

Yuzhang Shang, Dan Xu, Gaowen Liu et al.

Multi-task learning for dense prediction has emerged as a pivotal area in computer vision, enabling simultaneous processing of diverse yet interrelated pixel-wise prediction tasks. However, the substantial computational demands of state-of-the-art (SoTA) models often limit their widespread deployment. This paper addresses this challenge by introducing network binarization to compress resource-intensive multi-task dense predictors. Specifically, our goal is to significantly accelerate multi-task dense prediction models via Binary Neural Networks (BNNs) while maintaining and even improving model performance at the same time. To reach this goal, we propose a Binary Multi-task Dense Predictor, Bi-MTDP, and several variants of Bi-MTDP, in which a multi-task dense predictor is constructed via specified binarized modules. Our systematical analysis of this predictor reveals that performance drop from binarization is primarily caused by severe information degradation. To address this issue, we introduce a deep information bottleneck layer that enforces representations for downstream tasks satisfying Gaussian distribution in forward propagation. Moreover, we introduce a knowledge distillation mechanism to correct the direction of information flow in backward propagation. Intriguingly, one variant of Bi-MTDP outperforms full-precision (FP) multi-task dense prediction SoTAs, ARTC (CNN-based) and InvPT (ViT-Based). This result indicates that Bi-MTDP is not merely a naive trade-off between performance and efficiency, but is rather a benefit of the redundant information flow thanks to the multi-task architecture. Code is available at https://github.com/42Shawn/BiMTDP.

Hanrong Ye, Dan Xu

This report serves as a supplementary document for TaskPrompter, detailing its implementation on a new joint 2D-3D multi-task learning benchmark based on Cityscapes-3D. TaskPrompter presents an innovative multi-task prompting framework that unifies the learning of (i) task-generic representations, (ii) task-specific representations, and (iii) cross-task interactions, as opposed to previous approaches that separate these learning objectives into different network modules. This unified approach not only reduces the need for meticulous empirical structure design but also significantly enhances the multi-task network's representation learning capability, as the entire model capacity is devoted to optimizing the three objectives simultaneously. TaskPrompter introduces a new multi-task benchmark based on Cityscapes-3D dataset, which requires the multi-task model to concurrently generate predictions for monocular 3D vehicle detection, semantic segmentation, and monocular depth estimation. These tasks are essential for achieving a joint 2D-3D understanding of visual scenes, particularly in the development of autonomous driving systems. On this challenging benchmark, our multi-task model demonstrates strong performance compared to single-task state-of-the-art methods and establishes new state-of-the-art results on the challenging 3D detection and depth estimation tasks.

Dan Xu, Baofen Zheng, Qianqi Shen et al.

Job seekers often initiate search with short, underspecified queries. At LinkedIn, over 80% of job-related queries contain three or fewer keywords, making accurate user intent inference and relevant job retrieval particularly challenging. We present dynamic facet suggestion (DFS), an interactive query refinement mechanism that facilitates intent disambiguation by surfacing personalized semantic attributes conditioned on the joint user-query context in real time. We propose a policy-grounded, retrieval-augmented ranking framework for facet suggestion, comprising offline taxonomy curation, embedding-based retrieval of top-K candidates, and distilled small language model (SLM) based candidate scoring. The system is optimized for real-time serving via pointwise single-token scoring with batching and prefix caching. Offline evaluation demonstrates high precision for generated suggestions, and online A/B tests show significant improvements in suggestion engagement and job search outcomes.

Yuxin Wang, Lei Ke, Boqiang Zhang et al.

While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a novel unified framework that seamlessly integrates native 3D object perception with 3D-aware visual reasoning, enabling both precise 3D grounding and interpretable spatial understanding. Unlike conventional end-to-end models that directly predict answers from RGB/RGB-D inputs, our approach equips the model with native 3D object perception capabilities, enabling it to directly localize objects in 3D space based on textual descriptions. Building upon accurate 3D object localization, the model further performs explicit reasoning in 3D, achieving more interpretable and structured spatial understanding. To support robust training for these capabilities, we develop a scalable data construction pipeline that leverages depth estimation to lift large-scale 2D annotations into 3D space, significantly increasing the diversity and coverage for 3D object grounding data, yielding over six times larger than the largest existing single-image 3D detection dataset. Moreover, the pipeline generates spatial question-answering datasets that target chain-of-thought (CoT) reasoning in 3D, facilitating joint training for both 3D object localization and 3D spatial reasoning. Experimental results demonstrate that our unified framework not only achieves state-of-the-art performance on 3D grounding tasks, but also consistently surpasses existing methods in 3D spatial reasoning in vision-language model.

Hongjia Zhai, Qi Zhang, Xiaokun Pan et al.

Open-vocabulary scene understanding with online panoptic mapping is essential for embodied applications to perceive and interact with environments. However, existing methods are predominantly offline or lack instance-level understanding, limiting their applicability to real-world robotic tasks. In this paper, we propose OnlinePG, a novel and effective system that integrates geometric reconstruction and open-vocabulary perception using 3D Gaussian Splatting in an online setting. Technically, to achieve online panoptic mapping, we employ an efficient local-to-global paradigm with a sliding window. To build local consistency map, we construct a 3D segment clustering graph that jointly leverages geometric and semantic cues, fusing inconsistent segments within sliding window into complete instances. Subsequently, to update the global map, we construct explicit grids with spatial attributes for the local 3D Gaussian map and fuse them into the global map via robust bidirectional bipartite 3D Gaussian instance matching. Finally, we utilize the fused VLM features inside the 3D spatial attribute grids to achieve open-vocabulary scene understanding. Extensive experiments on widely used datasets demonstrate that our method achieves better performance among online approaches, while maintaining real-time efficiency.

Lihe Ding, Shaocong Dong, Yaokun Li et al.

Part-based 3D generation holds great potential for various applications. Previous part generators that represent parts using implicit vector-set tokens often suffer from insufficient geometric details. Another line of work adopts an explicit voxel representation but shares a global voxel grid among all parts; this often causes small parts to occupy too few voxels, leading to degraded quality. In this paper, we propose FullPart, a novel framework that combines both implicit and explicit paradigms. It first derives the bounding box layout through an implicit box vector-set diffusion process, a task that implicit diffusion handles effectively since box tokens contain little geometric detail. Then, it generates detailed parts, each within its own fixed full-resolution voxel grid. Instead of sharing a global low-resolution space, each part in our method - even small ones - is generated at full resolution, enabling the synthesis of intricate details. We further introduce a center-point encoding strategy to address the misalignment issue when exchanging information between parts of different actual sizes, thereby maintaining global coherence. Moreover, to tackle the scarcity of reliable part data, we present PartVerse-XL, the largest human-annotated 3D part dataset to date with 40K objects and 320K parts. Extensive experiments demonstrate that FullPart achieves state-of-the-art results in 3D part generation. We will release all code, data, and model to benefit future research in 3D part generation.

Yanan Liu, Jun Liu, Hao Zhang et al.

Skeleton-based action recognition has garnered significant attention in the computer vision community. Inspired by the recent success of the selective state-space model (SSM) Mamba in modeling 1D temporal sequences, we propose TSkel-Mamba, a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics. In particular, our approach leverages Spatial Transformer for spatial feature learning while utilizing Mamba for temporal modeling. Mamba, however, employs separate SSM blocks for individual channels, which inherently limits its ability to model inter-channel dependencies. To better adapt Mamba for skeleton data and enhance Mamba`s ability to model temporal dependencies, we introduce a Temporal Dynamic Modeling (TDM) block, which is a versatile plug-and-play component that integrates a novel Multi-scale Temporal Interaction (MTI) module. The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition. Extensive experiments on NTU-RGB+D 60, NTU-RGB+D 120, NW-UCLA and UAV-Human datasets demonstrate that TSkel-Mamba achieves state-of-the-art performance while maintaining low inference time, making it both efficient and highly effective.

Mingzheng Zhang, Jinfeng Gao, Dan Xu et al.

X-ray image-based medical report generation (MRG) is a pivotal area in artificial intelligence that can significantly reduce diagnostic burdens for clinicians and patient wait times. Existing MRG models predominantly rely on Large Language Models (LLMs) to improve report generation, with limited exploration of pre-trained vision foundation models or advanced fine-tuning techniques. Mainstream frameworks either avoid fine-tuning or utilize simplistic methods like LoRA, often neglecting the potential of enhancing cross-attention mechanisms. Additionally, while Transformer-based models dominate vision-language tasks, non-Transformer architectures, such as the Mamba network, remain underexplored for medical report generation, presenting a promising avenue for future research. In this paper, we propose EMRRG, a novel X-ray report generation framework that fine-tunes pre-trained Mamba networks using parameter-efficient methods. Specifically, X-ray images are divided into patches, tokenized, and processed by an SSM-based vision backbone for feature extraction, with Partial LoRA yielding optimal performance. An LLM with a hybrid decoder generates the medical report, enabling end-to-end training and achieving strong results on benchmark datasets. Extensive experiments on three widely used benchmark datasets fully validated the effectiveness of our proposed strategies for the X-ray MRG. The source code of this paper will be released on https://github.com/Event-AHU/Medical_Image_Analysis.

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

Yue Ma, Kunyu Feng, Zhongyuan Hu et al.

With the rapid development of AI-generated content (AIGC), video generation has emerged as one of its most dynamic and impactful subfields. In particular, the advancement of video generation foundation models has led to growing demand for controllable video generation methods that can more accurately reflect user intent. Most existing foundation models are designed for text-to-video generation, where text prompts alone are often insufficient to express complex, multi-modal, and fine-grained user requirements. This limitation makes it challenging for users to generate videos with precise control using current models. To address this issue, recent research has explored the integration of additional non-textual conditions, such as camera motion, depth maps, and human pose, to extend pretrained video generation models and enable more controllable video synthesis. These approaches aim to enhance the flexibility and practical applicability of AIGC-driven video generation systems. In this survey, we provide a systematic review of controllable video generation, covering both theoretical foundations and recent advances in the field. We begin by introducing the key concepts and commonly used open-source video generation models. We then focus on control mechanisms in video diffusion models, analyzing how different types of conditions can be incorporated into the denoising process to guide generation. Finally, we categorize existing methods based on the types of control signals they leverage, including single-condition generation, multi-condition generation, and universal controllable generation. For a complete list of the literature on controllable video generation reviewed, please visit our curated repository at https://github.com/mayuelala/Awesome-Controllable-Video-Generation.

Zhenxing Mi, Ping Yin, Xue Xiao et al.

Recent NeRF methods on large-scale scenes have underlined the importance of scene decomposition for scalable NeRFs. Although achieving reasonable scalability, there are several critical problems remaining unexplored, i.e., learnable decomposition, modeling scene heterogeneity, and modeling efficiency. In this paper, we introduce Switch-NeRF++, a Heterogeneous Mixture of Hash Experts (HMoHE) network that addresses these challenges within a unified framework. It is a highly scalable NeRF that learns heterogeneous decomposition and heterogeneous NeRFs efficiently for large-scale scenes in an end-to-end manner. In our framework, a gating network learns to decompose scenes and allocates 3D points to specialized NeRF experts. This gating network is co-optimized with the experts by our proposed Sparsely Gated Mixture of Experts (MoE) NeRF framework. We incorporate a hash-based gating network and distinct heterogeneous hash experts. The hash-based gating efficiently learns the decomposition of the large-scale scene. The distinct heterogeneous hash experts consist of hash grids of different resolution ranges, enabling effective learning of the heterogeneous representation of different scene parts. These design choices make our framework an end-to-end and highly scalable NeRF solution for real-world large-scale scene modeling to achieve both quality and efficiency. We evaluate our accuracy and scalability on existing large-scale NeRF datasets and a new dataset with very large-scale scenes ($>6.5km^2$) from UrbanBIS. Extensive experiments demonstrate that our approach can be easily scaled to various large-scale scenes and achieve state-of-the-art scene rendering accuracy. Furthermore, our method exhibits significant efficiency, with an 8x acceleration in training and a 16x acceleration in rendering compared to Switch-NeRF. Codes will be released at https://github.com/MiZhenxing/Switch-NeRF.

Fa-Ting Hong, Li Shen, Dan Xu

Predominant techniques on talking head generation largely depend on 2D information, including facial appearances and motions from input face images. Nevertheless, dense 3D facial geometry, such as pixel-wise depth, plays a critical role in constructing accurate 3D facial structures and suppressing complex background noises for generation. However, dense 3D annotations for facial videos is prohibitively costly to obtain. In this work, firstly, we present a novel self-supervised method for learning dense 3D facial geometry (ie, depth) from face videos, without requiring camera parameters and 3D geometry annotations in training. We further propose a strategy to learn pixel-level uncertainties to perceive more reliable rigid-motion pixels for geometry learning. Secondly, we design an effective geometry-guided facial keypoint estimation module, providing accurate keypoints for generating motion fields. Lastly, we develop a 3D-aware cross-modal (ie, appearance and depth) attention mechanism, which can be applied to each generation layer, to capture facial geometries in a coarse-to-fine manner. Extensive experiments are conducted on three challenging benchmarks (ie, VoxCeleb1, VoxCeleb2, and HDTF). The results demonstrate that our proposed framework can generate highly realistic-looking reenacted talking videos, with new state-of-the-art performances established on these benchmarks. The codes and trained models are publicly available on the GitHub project page at https://github.com/harlanhong/CVPR2022-DaGAN

Zhenxing Mi, Di Chang, Dan Xu

Multi-view Stereo (MVS) with known camera parameters is essentially a 1D search problem within a valid depth range. Recent deep learning-based MVS methods typically densely sample depth hypotheses in the depth range, and then construct prohibitively memory-consuming 3D cost volumes for depth prediction. Although coarse-to-fine sampling strategies alleviate this overhead issue to a certain extent, the efficiency of MVS is still an open challenge. In this work, we propose a novel method for highly efficient MVS that remarkably decreases the memory footprint, meanwhile clearly advancing state-of-the-art depth prediction performance. We investigate what a search strategy can be reasonably optimal for MVS taking into account of both efficiency and effectiveness. We first formulate MVS as a binary search problem, and accordingly propose a generalized binary search network for MVS. Specifically, in each step, the depth range is split into 2 bins with extra 1 error tolerance bin on both sides. A classification is performed to identify which bin contains the true depth. We also design three mechanisms to respectively handle classification errors, deal with out-of-range samples and decrease the training memory. The new formulation makes our method only sample a very small number of depth hypotheses in each step, which is highly memory efficient, and also greatly facilitates quick training convergence. Experiments on competitive benchmarks show that our method achieves state-of-the-art accuracy with much less memory. Particularly, our method obtains an overall score of 0.289 on DTU dataset and tops the first place on challenging Tanks and Temples advanced dataset among all the learning-based methods. The trained models and code will be released at https://github.com/MiZhenxing/GBi-Net.

Yinmin Zhang, Xinzhu Ma, Shuai Yi et al.

As a crucial task of autonomous driving, 3D object detection has made great progress in recent years. However, monocular 3D object detection remains a challenging problem due to the unsatisfactory performance in depth estimation. Most existing monocular methods typically directly regress the scene depth while ignoring important relationships between the depth and various geometric elements (e.g. bounding box sizes, 3D object dimensions, and object poses). In this paper, we propose to learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. We further implement and embed the proposed formula to enable geometry-aware deep representation learning, allowing effective 2D and 3D interactions for boosting the depth estimation. Moreover, we provide a strong baseline through addressing substantial misalignment between 2D annotation and projected boxes to ensure robust learning with the proposed geometric formula. Experiments on the KITTI dataset show that our method remarkably improves the detection performance of the state-of-the-art monocular-based method without extra data by 2.80% on the moderate test setting. The model and code will be released at https://github.com/YinminZhang/MonoGeo.

Jiapeng Tang, Jiabao Lei, Dan Xu et al.

Surface reconstruction from point clouds is a fundamental problem in the computer vision and graphics community. Recent state-of-the-arts solve this problem by individually optimizing each local implicit field during inference. Without considering the geometric relationships between local fields, they typically require accurate normals to avoid the sign conflict problem in overlapped regions of local fields, which severely limits their applicability to raw scans where surface normals could be unavailable. Although SAL breaks this limitation via sign-agnostic learning, further works still need to explore how to extend this technique for local shape modeling. To this end, we propose to learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks, to simultaneously achieve advanced scalability to large-scale scenes, generality to novel shapes, and applicability to raw scans in a unified framework. Concretely, we achieve this goal by a simple yet effective design, which further optimizes the pre-trained occupancy prediction networks with an unsigned cross-entropy loss during inference. The learning of occupancy fields is conditioned on convolutional features from an hourglass network architecture. Extensive experimental comparisons with previous state-of-the-arts on both object-level and scene-level datasets demonstrate the superior accuracy of our approach for surface reconstruction from un-orientated point clouds. The code is available at https://github.com/tangjiapeng/SA-ConvONet.

Jiapeng Tang, Dan Xu, Kui Jia et al.

This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how to design a flexible framework for learning robust spatio-temporal shape representations from 4D point clouds, and develop an efficient mechanism for capturing shape dynamics. In this work, we present a novel pipeline to learn a temporal evolution of the 3D human shape through spatially continuous transformation functions among cross-frame occupancy fields. The key idea is to parallelly establish the dense correspondence between predicted occupancy fields at different time steps via explicitly learning continuous displacement vector fields from robust spatio-temporal shape representations. Extensive comparisons against previous state-of-the-arts show the superior accuracy of our approach for 4D human reconstruction in the problems of 4D shape auto-encoding and completion, and a much faster network inference with about 8 times speedup demonstrates the significant efficiency of our approach. The trained models and implementation code are available at https://github.com/tangjiapeng/LPDC-Net.