论文检索

Bin Yang, Mohamed Abdelsamad, Miao Zhang, Alexandru Paul Condurache

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across augmented views or by masked scene modeling. However, the resulting representations transfer poorly to instance localization, and often require full finetuning for strong performance. Instance awareness is a fundamental component of 3D perception, thus bridging this gap is crucial for progressing toward true 3D foundation models that support all downstream tasks on 3D data. In this work, we introduce PointINS, an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning.PointINS employs an orthogonal offset branch to jointly learn high-level semantic understanding and geometric reasoning, yielding instance awareness. We identify two consistent properties essential for robust instance localization and formulate them as complementary regularization strategies, Offset Distribution Regularization (ODR), which aligns predicted offsets with empirically observed geometric priors, and Spatial Clustering Regularization (SCR), which enforces local coherence by regularizing offsets with pseudo-instance masks. Through extensive experiments across five datasets, PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation, paving the way for scalable 3D foundation models.

Angel Daruna, Nicholas Meegan, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar

Worldwide visual geo-localization aims to determine the geographic location of an image anywhere on Earth using only its visual content. Despite recent progress, learning expressive representations of geographic space remains challenging due to the inherently low-dimensional nature of geographic coordinates. We formulate global geo-localization as aligning the visual representation of a query image with a learned geographic representation. Our approach explicitly models the world as a hierarchy of learned geographic embeddings, enabling a distributed and multi-scale representation of geographic space. In addition, we introduce a semantic fusion module that efficiently integrates appearance features with semantic segmentation through latent cross-attention, producing a more robust visual representation for localization. Experiments on five widely used geo-localization benchmarks demonstrate that our method achieves new state-of-the-art results on 22 of 25 reported metrics. Ablation studies show that these improvements are primarily driven by the proposed geographic representation and semantic fusion mechanism.

Xingkui Zhu, Dingkang Liang, Cheng Chen, Daoxin Zhang, lv Hanxiang, Zhe Xu, Yao Hu, Xiang Bai

Sparse activation layers, primarily Mixture-of-Experts (MoE) and memory-based modules, have become a central approach for scaling large models and are gaining traction in vision tasks. Despite conceptual similarities, these paradigms have evolved independently, hindering systematic comparison and the development of modules that exploit their complementary strengths. To bridge this gap, we propose OneSparse, a unified framework that reformulates MoE and memory modules under a common abstraction. This enables their systematic comparison and integration, revealing a continuous design space. Guided by this abstraction, we design the Nexus Layer, which features two key innovations: a unified routing mechanism that combines the efficiency of memory retrieval with MoE's load balancing to ensure stable and scalable token assignment, and an adaptive processing strategy where memory modules sketch coarse representations while expert modules refine critical regions. Extensive experiments on image classification, object detection, and semantic segmentation demonstrate that our Nexus Layer establishes a new performance--efficiency frontier, surpassing representative sparse baselines across convolutional and Transformer architectures. These results validate the power of the OneSparse framework to unify and integrate complementary sparse paradigms and underscore the potential of hybrid sparse modeling in vision.

Vanessa Emanuela Guarino, Claudia Winklmayr, Jannik Franzen, Josef Lorenz Rumberger, Manuel Pfeuffer, Sonja Greven, Klaus Maier-Hein, Dagmar Kainmueller, Christoph Karg, Carsten T. Lüth

Uncertainty Quantification (UQ) is crucial for ensuring the reliability of automated image segmentations in safety-critical domains like biomedical image analysis or autonomous driving. In segmentation, UQ generates pixel-wise uncertainty scores that must be aggregated into image-level scores for downstream tasks like Out-of-Distribution (OoD) or failure detection. Despite routine use of aggregation strategies, their properties and impact on downstream task performance have not yet been comprehensively studied. Global Average is the default choice, yet it does not account for spatial and structural features of segmentation uncertainty. Alternatives like patch-, class- and threshold-based strategies exist, but lack systematic comparison, leading to inconsistent reporting and unclear best practices. We address this gap by (1) formally analyzing properties, limitations, and pitfalls of common strategies; (2) proposing novel strategies that incorporate spatial uncertainty structure and (3) benchmarking their performance on OoD and failure detection across ten datasets that vary in image geometry and structure. We find that aggregators leveraging spatial structure yield stronger performance in both downstream tasks studied. However, the performance of individual aggregators depends heavily on dataset characteristics, so we (4) propose a meta-aggregator that integrates multiple aggregators and performs robustly across datasets.

Gaoge Han, Yongkang Cheng, Zhe Chen, Shaoli Huang, Tongliang Liu

Two-hand reconstruction from monocular images is hampered by complex poses and severe occlusions, which often cause interaction misalignment and two-hand penetration. We address this by decoupling the problem into 2D structural alignment and 3D spatial interaction alignment, each handled by a tailored component. For 2D alignment, we pioneer the attempt to unify heterogeneous structural priors (keypoints, segmentation, and depth) from vision foundation models as complementary structured guidance for two-hand recovery. Instead of extracting priors prediction as explicit inputs, we propose a fusion-alignment encoder that absorbs their structural knowledge implicitly, achieving foundation-level guidance without foundation-level cost. For 3D spatial alignment, we propose a two-hand penetration-free diffusion model that learns a generative mapping from interpenetrated poses to realistic, collision-free configurations. Guided by collision gradients during denoising, the model converges toward the manifold of valid two-hand interactions, preserving geometric and kinematic coherence. This generative formulation approach enables physically credible reconstructions even under occlusion or ambiguous visual input. Extensive experiments on InterHand2.6M and HIC show state-of-the-art or leading performance in interaction alignment and penetration suppression. Project: https://gaogehan.github.io/A2P/

Fang Liu, Yuhao Liu, Ke Xu, Gerhard Petrus Hancke, Rynson W. H. Lau

In this paper, we propose GenSplat, a novel approach for language comprehension in 3D Gaussian Splatting (3DGS). Unlike previous methods that either achieve cross-scene generalization by being bounded to a predefined vocabulary or handle free-form language by overfitting to individual scenes, GenSplat is robust to free-form language queries and generalizable across 3DGS scene representations. Our key insight for this problem is to formulate a structured learning process to progressively align linguistic concepts with 3D Gaussians. It contains two novel technical contributions. First, we propose a Progressive Language Grounding Curriculum that structurally guides the model through learning category-level semantics to instance-level concepts and free-form language, preventing overfitting by building a generalizable language feature space. Second, we design a Multi-modal Large Language Models (MLLM)-guided Reasoning Module that leverages MLLM's semantic and spatial priors to enhance 3D localization and reasoning. To further improve spatial alignment and computational efficiency, we introduce a GeometryAware Frame Selector (GAFS), which adaptively selects the most informative views based on Gaussian and textural cues. Extensive cross-task evaluations (including 3D referring segmentation, 3D visual question answering, and 3D open-vocabulary understanding) demonstrate state-of-the-art performances and strong generalization capability of GenSplat. We will release the codes.

Ali Hojjat, Janek Haberer, Sören Pirk, Olaf Landsiedel

ViTs deliver SOTA performance, yet their fixed computational budget prevents scalable deployment across heterogeneous hardware. Recent Matryoshka-style Transformer architectures mitigate this by embedding nested subnetworks within a single model to enable scalable inference. However, these models allocate the same amount of compute to all inputs, regardless of their complexity, which leads to inefficiencies. To address this, we introduce ThinkingViT, a nested ViT architecture that employs progressive thinking stages to dynamically adjust inference computation based on input difficulty. ThinkingViT first activates a small subset of the most important attention heads to produce an initial prediction. If the prediction confidence exceeds a predefined threshold, inference terminates early. Otherwise, within the same backbone, it activates a larger subset of attention heads and conducts a new forward pass. This process continues iteratively until the model reaches the predefined confidence level or exhausts its maximum capacity. To boost the performance of subsequent rounds, we introduce a Token Recycling approach that fuses the input embeddings with the embeddings from the previous stage. Experiments show that ThinkingViT surpasses nested baselines by up to 2.0 percentage points (p.p.) in accuracy at the same throughput and by up to 2.9 p.p. at equal GMACs on ImageNet-1K. We show that the backbone-preserving design of ThinkingViT allows it to serve as a plug-in upgrade for ViTs in downstream tasks such as semantic segmentation. We also demonstrate that ThinkingViT transfers effectively to other architectures such as Swin Transformers.

Houji Wen, Jiangyong Yu, Dawei Yang, Jun Li

Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to their high computational and memory demands. Post-Training Quantization (PTQ) is a widely used technique for model compression and acceleration. However, existing PTQ methods fail to consider the cross-attention architecture in the SAM decoder. This degradation primarily stems from the unique challenges posed by SAMs: (1) Attention dissipation, where the attention information in the decoder, which is crucial for representing segmentation masks, collapses into a diffuse and non-semantic form under low-bit quantization; and (2) Reconstruction oscillation, where bidirectional coupling within the two-way transformer introduces cross-branch error interference and destabilizes convergence. To tackle these issues, we propose CAR-SAM, a unified quantization framework tailored for SAMs. Firstly, to mitigate attention dissipation, we introduce MatMul-Aware Compensation (MAC) mechanism that transfers activation-induced quantization errors from MatMul to preceding linear weights. Secondly, to mitigate oscillation in decoder optimization, we develop a Joint Cross-Attention Reconstruction (JCAR) strategy that jointly reconstructs coupled attention branches, suppressing oscillatory behavior and promoting stable convergence. Extensive experiments show that CAR-SAM robustly quantizes SAM models down to 4-bit precision, surpassing existing methods by 14.6% and 6.6% mAP on SAM-B and SAM-L respectively.

Yu Wang, Shengjie Zhao

Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only video-level annotations are provided as supervisory signals. However, a key limitation persists in WS-VAD, as dense frame-level annotations are absent, which often leaves existing methods struggling to learn anomaly semantics effectively. To address this issue, we propose a novel framework named LAS-VAD, short for Learning Anomaly Semantics for WS-VAD, which integrates anomaly-connected component mechanism and intention awareness mechanism. The former is designed to assign video frames into distinct semantic groups within a video, and frame segments within the same group are deemed to share identical semantic information. The latter leverages an intention-aware strategy to distinguish between similar normal and abnormal behaviors (e.g., taking items and stealing). To further model the semantic information of anomalies, as anomaly occurrence is accompanied by distinct characteristic attributes (i.e., explosions are characterized by flames and thick smoke), we additionally incorporate anomaly attribute information to guide accurate detection. Extensive experiments on two benchmark datasets, XD-Violence and UCF-Crime, demonstrate that our LAS-VAD outperforms current state-of-the-art methods with remarkable gains.

Chenguo Lin, Yuchen Lin, Panwang Pan, Yifan Yu, Tao Hu, Honglei Yan, Katerina Fragkiadaki, Yadong Mu

We present MoVieS, a Motion-aware View Synthesis model that reconstructs 4D dynamic scenes from monocular videos in one second. It represents dynamic 3D scenes with pixel-aligned Gaussian primitives and explicitly supervises their time-varying motions. This allows, for the first time, the unified modeling of appearance, geometry and motion from monocular videos, and enables reconstruction, view synthesis and 3D point tracking within a single learning-based framework. By bridging view synthesis with geometry reconstruction, MoVieS enables large-scale training on diverse datasets with minimal dependence on task-specific supervision. As a result, it also naturally supports a wide range of zero-shot applications, such as scene flow estimation and moving object segmentation. Extensive experiments validate the effectiveness and efficiency of MoVieS across multiple tasks, achieving competitive performance while offering several orders of magnitude speedups.

Viktor Zaytsev, Olena Vynokurova, Pavlo Tytarchuk, Dmytro Kozii, Vitalii Pohribnyi, Olga Radyvonenko, Artem Shcherbina

Table structure recognition in document AI faces significant challenges due to layout inconsistencies, merged cells, and complex nested structures, which is further exacerbated by the scarcity of large, diverse annotated datasets. In this paper, we present PIX-TAB (Efficient PIXel-Precise TABle Structure Recognition Approach) that provides exact, pixel-level structure using a small, lightweight model that can run on-device. The approach is language-agnostic, as it allows adding support for a new languages simply by replacing the Optical Character Recognition (OCR) model without modifying to the core structure recognition model. Key innovations include: position-aware pixel-precise tokens for deterministic cell reconstruction; speculative decoding for faster sequence generation, and training-only box supervision to stabilize spatial grounding; region-based image segmentation. To mitigate data scarcity we propose a pipeline for generating a large synthetic table dataset. Experimental results validate each component. To address the limitations of existing evaluation methods we introduce TEDS_ struct100 and TEDS_ 100 metrics. Speculative decoding approach significantly improves recognition speed while maintaining accuracy. Finally, the combined techniques enable a mobile-optimized model that is more than three times faster than the full-size version.

Jiahao Chen, Zihui Zhang, Yafei Yang, Jinxi Li, Shenxing Wei, Zhixuan Sun, Bo Yang

We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when transferring object priors from synthetic datasets (e.g., ShapeNet) to real scans (e.g., ScanNet), particularly due to morphological variations and occlusion artifacts. To address this, EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects. We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results.

Chonghua Lv, Dong Zhao, Shuang Wang, Dou Quan, Ning Huyan, Nicu Sebe, Zhun Zhong

Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under distribution shifts. This limitation becomes more severe with the emergence of vision foundation models (VFMs): although VFMs exhibit strong robustness on unseen data, distilling them with conventional KD often compromises this ability. We propose Generalizable Knowledge Distillation (GKD), a multi-stage framework that explicitly enhances generalization. GKD decouples representation learning from task learning. In the first stage, the student acquires domain-agnostic representations through selective feature distillation, and in the second stage, these representations are frozen for task adaptation, thereby mitigating overfitting to visible domains. To further support transfer, we introduce a query-based soft distillation mechanism, where student features act as queries to teacher representations to selectively retrieve transferable spatial knowledge from VFMs. Extensive experiments on five domain generalization benchmarks demonstrate that GKD consistently outperforms existing KD methods, achieving average gains of +1.9% in foundation-to-foundation (F2F) and +10.6% in foundation-to-local (F2L) distillation. The code will be available at https://github.com/Younger-hua/GKD.

Mingfang Zhang, Jingjing Pan, Ashutosh Kumar, Rajat Saini, Mustafa Erdogan, Hsuan-Kung Yang, Caixin Kang, Yifei Huang, Yoichi Sato, Quan Kong

Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely provide the fine-grained, grounded evidence needed to rigorously evaluate this capability. To address this gap, we introduce CaST-Bench, a benchmark for Causal Chain-Grounded Spatio-Temporal Video Reasoning. CaST-Bench presents complex causal questions that require models to identify and localize a chain of multiple spatio-temporal evidences. Through a human-AI collaborative pipeline, we construct a high-quality dataset of 2,066 questions over 1,015 videos, with causal chains annotated by temporal segments and bounding-box tracks. Furthermore, we design a comprehensive evaluation suite with novel metrics that assess not only answer correctness but also the capability for visual evidence grounded reasoning. This grounding is crucial for improving accuracy by mitigating spurious correlations and for enhancing user trust by making models more transparent. Our experiments show that current VLMs struggle with causal questions, largely due to their limited ability to construct precise and grounded causal chains. This highlights an important direction for improving future VLMs.

Rafi Ibn Sultan, Hui Zhu, Xiangyu Zhou, Chengyin Li, Prashant Khanduri, Marco Brocanelli, Dongxiao Zhu

Ensuring accessible pedestrian navigation requires reasoning about both semantic and spatial aspects of complex urban scenes, a challenge that existing Large Vision-Language Models (LVLMs) struggle to meet. Although these models can describe visual content, their lack of explicit grounding leads to object hallucinations and unreliable depth reasoning, limiting their usefulness for accessibility guidance. We introduce WalkGPT, a pixel-grounded LVLM for the new task of Grounded Navigation Guide, unifying language reasoning and segmentation within a single architecture for depth-aware accessibility guidance. Given a pedestrian-view image and a navigation query, WalkGPT generates a conversational response with segmentation masks that delineate accessible and harmful features along with relative depth estimation. The model incorporates a Multi-Scale Query Projector (MSQP) that shapes the final image tokens by aggregating them along text tokens across spatial hierarchies, and a Calibrated Text Projector (CTP), guided by a Region Alignment Loss, that maps language embeddings into segmentation-aware representations. These components enable fine-grained grounding and depth inference without user-provided cues or anchor points, allowing the model to generate complete and realistic navigation guidance. We also introduce PAVE, a large-scale benchmark of 41k pedestrian-view images paired with accessibility-aware questions and depth-grounded answers. Experiments show that WalkGPT achieves strong grounded reasoning and segmentation performance. The source code and dataset are available on the project website.

Haiyang Mei, Qiming Huang, Hai Ci, Mike Zheng Shou

Accurate robot segmentation is a fundamental capability for robotic perception. It enables precise visual servoing for VLA systems, scalable robot-centric data augmentation, accurate real-to-sim transfer, and reliable safety monitoring in dynamic human-robot environments. Despite the strong capabilities of modern segmentation models, surprisingly it remains challenging to segment robots. This is due to robot embodiment diversity, appearance ambiguity, structural complexity, and rapid shape changes. Embracing these challenges, we introduce RobotSeg, a foundation model for robot segmentation in image and video. RobotSeg is built upon the versatile SAM 2 foundation model but addresses its three limitations for robot segmentation, namely the lack of adaptation to articulated robots, reliance on manual prompts, and the need for per-frame training mask annotations, by introducing a structure-enhanced memory associator, a robot prompt generator, and a label-efficient training strategy. These innovations collectively enable a structure-aware, automatic, and label-efficient solution. We further construct the video robot segmentation (VRS) dataset comprising over 2.8k videos (138k frames) with diverse robot embodiments and environments. Extensive experiments demonstrate that RobotSeg achieves state-of-the-art performance on both images and videos, establishing a strong foundation for future advances in robot perception.

Haoyu Ji, Xueting Liu, Yu Gao, Wenze Huang, Zhihao Yang, Weihong Ren, Zhiyong Wang, Honghai Liu

Skeleton-based Temporal Action Segmentation (STAS) aims to densely parse untrimmed skeletal sequences into frame-level action categories. However, existing methods, while proficient at capturing spatio-temporal kinematics, neglect the underlying physical dynamics that govern human motion. This oversight limits inter-class discriminability between actions with similar kinematics but distinct dynamic intents, and hinders precise boundary localization where dynamic force profiles shift. To address these, we propose the Lagrangian-Dynamic Informed Network (LaDy), a framework integrating principles of Lagrangian dynamics into the segmentation process. Specifically, LaDy first computes generalized coordinates from joint positions and then estimates Lagrangian terms under physical constraints to explicitly synthesize the generalized forces. To further ensure physical coherence, our Energy Consistency Loss enforces the work-energy theorem, aligning kinetic energy change with the work done by the net force. The learned dynamics then drive a Spatio-Temporal Modulation module: Spatially, generalized forces are fused with spatial representations to provide more discriminative semantics. Temporally, salient dynamic signals are constructed for temporal gating, thereby significantly enhancing boundary awareness. Experiments on challenging datasets show that LaDy achieves state-of-the-art performance, validating the integration of physical dynamics for action segmentation. Code is available at https://github.com/HaoyuJi/LaDy.

Dong Zhao, Qi Zang, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong

Domain Generalization in Semantic Segmentation (DG-SS) aims to enable segmentation models to perform robustly in unseen environments. However, conventional DG-SS methods are restricted to a fixed set of known categories, limiting their applicability in open-world scenarios. Recent progress in Vision-Language Models (VLMs) has advanced Open-Vocabulary Semantic Segmentation (OV-SS) by enabling models to recognize a broader range of concepts. Yet, these models remain sensitive to domain shifts and struggle to maintain robustness when deployed in unseen environments, a challenge that is particularly severe in urban-driving scenarios. To bridge this gap, we introduce Open-Vocabulary Domain Generalization in Semantic Segmentation (OVDG-SS), a new setting that jointly addresses unseen domains and unseen categories. We introduce the first benchmark for OVDG-SS in autonomous driving, addressing a previously unexplored problem and covering both synthetic-to-real and real-to-real generalization across diverse unseen domains and unseen categories. In OVDG-SS, we observe that domain shifts often distort text-image correlations in pre-trained VLMs, which hinders the performance of OV-SS models. To tackle this challenge, we propose S^2-Corr, a state-space-driven text-image correlation refinement mechanism that can mitigate domain-induced distortions and produce a more consistent text-image correlation under distribution changes. Extensive experiments on our constructed benchmark demonstrate that the proposed method achieves superior cross-domain performance and efficiency compared to existing OV-SS approaches.

Shihao Wang, Guo Chen, De-An Huang, Zhiqi Li, Minghan Li, Guilin Liu, Jan Kautz, Jose M. Alvarez, Lei Zhang, Zhiding Yu

While Video Large Language Models (Video-LLMs) have shown significant potential in multimodal understanding and reasoning tasks, how to efficiently select the most informative frames from videos remains a critical challenge. Existing methods attempt to optimize frame sampling by reducing inter-frame redundancy or employing unsupervised event localization. However, these approaches often fall short in handling complex instruction-following tasks and scenarios that demand precise temporal modeling, resulting in limited performance in both semantic alignment and temporal reasoning. To address the above challenges, we introduce Instructed Temporal Grounding for Videos (VideoITG), a framework aiming to adaptively customize frame sampling strategies based on user instructions. Specifically, we design the VidThinker pipeline, which automates annotation by generating instruction-conditioned captions, retrieving relevant video segments, and selecting key frames to enable efficient supervision. Using VidThinker, we build the VideoITG-40K dataset with 40K videos and 500K temporal grounding annotations. Our plug-and-play VideoITG model leverages Video-LLMs' visual-language alignment and reasoning for discriminative frame selection. VideoITG consistently boosts the performance on multiple multimodal video understanding benchmarks, demonstrating its effectiveness and potential.

Xianjie Liu, Keren Fu, Qijun Zhao

High-precision dichotomous image segmentation (DIS) is a task of extracting fine-grained objects from high-resolution images.Existing methods trade efficiency for accuracy: non-diffusion methods are fast but suffer from weak semantics and unstable spatial priors, causing false detections; diffusion-based methods offer high accuracy via strong generative priors but are computationally expensive.In depth maps, a complete object appears as a low variance region with a smooth interior and sharp boundaries, whereas the background exhibits a chaotic, high variance pattern due to disconnected surfaces at varying depths. We refer to this as the depth integrity-prior.Inspired by this, and noting that DIS currently lacks depth maps, we leverage pseudo-depth information from monocular depth estimation models to obtain essential semantic understanding, thereby rapidly revealing spatial differences across target objects and the background.To exploit this prior, we propose the Prior-guided Depth Fusion Network (PDFNet), which fuses RGB and pseudo-depth features for depth-aware structure perception. We further introduce a novel depth integrity-prior loss to enforce depth consistency in segmentation and a fine-grained enhancement module with adaptive patch selection to sharpen boundaries.Notably, PDFNet with DAM-v2 achieves SOTA (F^ max _b 0.915 on DIS-VD and 0.915 on DIS-TE) using less than half the params of diffusion-based methods.