GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
Tongji University（同济大学）；Hong Kong Polytechnic University（香港理工大学）；Tencent（腾讯）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））
Hongchang Liu, Jian Liu, Yujuan Ding, Liang Peng, Xun Jiang, Fei Ma, Xing Xu, Yi Bin
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view dependence of these features entangles scene dynamics with camera-induced variation, making the resulting state evolution harder to predict. We propose GeoState, a view-decoupled geometry representation for predictive 3D world modeling that separates scene-state evolution from camera-dependent observation. Specifically, a scene tokenizer aggregates multi-view GFM features into a view-decoupled scene state, which a geometry decoder queries using camera rays. An autoregressive world model then predicts future scene states, while camera motion is modeled separately. The predicted states can therefore be decoded under either predicted or externally specified cameras, while retaining a single context-derived scale throughout the rollout without per-frame scale alignment. Experiments show that GeoState outperforms prior 3D world models on Waymo, supports geometrically consistent cross-view querying, and generalizes zero-shot to KITTI and nuScenes. Project page: https://hongchang-liu.github.io/GeoState-project-page/
Microsoft Research Asia（微软亚洲研究院）；Tsinghua University（清华大学）
Layout generation aims to synthesize realistic graphic scenes consisting of elements with different attributes including category, size, position, and between-element relation. It is a crucial task for reducing the burden on heavy-duty graphic design works for formatted scenes, e.g., publications, documents, and user interfaces (UIs). Diverse application scenarios impose a big challenge in unifying various layout generation subtasks, including conditional and unconditional generation. In this paper, we propose a Layout Diffusion Generative Model (LDGM) to achieve such unification with a single…
Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
Institute of Trustworthy Embodied AI (TEAI)（可信具身人工智能研究院）；Sch. of Computer Science & Sch. of Artificial Intelligence（计算机科学学院与人工智能学院）；Shanghai Jiao Tong University（上海交通大学）
WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；KlingAI；The University of Hong Kong（香港大学）
Hefei University of Technology（合肥工业大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Zhejiang University（浙江大学）；Sea AI Lab（Sea人工智能实验室）
Low-light stereo image enhancement (LLSIE) is a relatively new task to enhance the quality of visually unpleasant stereo images captured in dark condition. However, current methods achieve inferior performance on detail recovery and illumination adjustment. We find it is because: 1) the insufficient single-scale inter-view interaction makes the cross-view cues unable to be fully exploited; 2) lacking long-range dependency leads to the inability to deal with the spatial long-range effects caused by illumination degradation. To alleviate such limitations, we propose a LLSIE model termed Decouple…
UltraGS: Real-Time Physically-Decoupled Gaussian Splatting for Ultrasound Novel View Synthesis
2 Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China；3 School of Medicine, Nankai University, Tianjin, China；4 School of Medicine, Anhui University of Science \& Technology, Huainan, China
DriveExplorer: Images-Only Decoupled 4D Reconstruction with Progressive Restoration for Driving View Extrapolation
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东省级超高清沉浸媒体技术重点实验室）；School of Electronic and Computer Engineering（电子与计算机工程学院）；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）
Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research A*STAR（新加坡资讯通信研究院（新加坡科技研究局下属））；Centre for Frontier AI Research, A*STAR（新加坡前沿人工智能研究院（新加坡科技研究局下属））
View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network
School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）；Department of Electrical and Computer Engineering, Johns Hopkins University（约翰霍普金斯大学电气与计算机工程系）；Pazhou Lab (HuangPu)（琶洲实验室（黄埔））；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（机器智能与先进计算教育部重点实验室）
EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography
Shanghai Children’s Medical Center, School of Medicine, Shanghai Jiao Tong University（上海交通大学医学院附属上海儿童医学中心）；Shanghai Engineering Research Center of Intelligence Pediatrics (SERCIP)（上海智能儿科工程技术研究中心）；East China Normal University（华东师范大学）；University of Shanghai for Science and Technology（上海理工大学）
Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT
Department of Electrical and Computer Engineering, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校电子与计算机工程系）；School of Biomedical Engineering, Sun Yat-Sen University（中山大学生物医学工程学院）
GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（南京航空航天大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Department of Computing, Hong Kong Polytechnic University（香港理工大学计算学系）；School of Computer Science, Peking University（北京大学计算机科学学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy（广东省人工智能与数字经济实验室）；Huawei Consumer Business Group, Huawei（华为消费者业务集团）；Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）
State-of-the-art distillation methods are mainly based on distilling deep features from intermediate layers, while the significance of logit distillation is greatly overlooked. To provide a novel viewpoint to study logit distillation, we reformulate the classical KD loss into two parts, i.e., target class knowledge distillation (TCKD) and non-target class knowledge distillation (NCKD). We empirically investigate and prove the effects of the two parts: TCKD transfers knowledge concerning the "difficulty" of training samples, while NCKD is the prominent reason why logit distillation works. More …
Automating the analysis of surveillance video footage is of great interest when urban environments or industrial sites are monitored by a large number of cameras. As anomalies are often context-specific, it is hard to predefine events of interest and collect labelled training data. A purely unsupervised approach for automated anomaly detection is much more suitable. For every camera, a separate algorithm could then be deployed that learns over time a baseline model of appearance and motion related features of the objects within the camera viewport. Anything that deviates from this baseline is …
Hainan University（海南大学）；Wuhan University of Technology（武汉理工大学）；Beijing Jiaotong University（北京交通大学）；Shenzhen University（深圳大学）；City University of Hong Kong（香港城市大学）；City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）
Stereo superpixel segmentation aims at grouping the discretizing pixels into perceptual regions through left and right views more collaboratively and efficiently. Existing superpixel segmentation algorithms mostly utilize color and spatial features as input, which may impose strong constraints on spatial information while utilizing the disparity information in terms of stereo image pairs. To alleviate this issue, we propose a stereo superpixel segmentation method with a decoupling mechanism of spatial information in this work. To decouple stereo disparity information and spatial information, t…
