3D 视觉

CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning

Peiwen Xia, Tangfei Liao, Wei Zhu, Danhuai Zhao, Jianjun Ke, Kaihao Zhang, Tong Lu, Tao Wang

机构 * Nanjing University（南京大学） ； China Mobile Zijin Innovation Institute（中国移动 zigin 创新院） ； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments Accepted by ECAI 2025

MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network

Jianfei Jiang, Qiankun Liu, Haochen Yu, Hongyuan Liu, Liyong Wang, Jiansheng Chen, Huimin Ma

机构 * University of Science and Technology Beijing（北京科技大学） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025

Advancing Depth Anything Model for Unsupervised Monocular Depth Estimation in Endoscopy

Bojian Li, Bo Liu, Xinning Yao, Jinghua Yue, Fugen Zhou

机构 * Image Processing Center, Beihang University（北京航空航天大学图像处理中心） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments Accepted by IROS2025, 8 pages, 7 figures

A Practical Approach to Underwater Depth and Surface Normals Estimation

Alzayat Saleh, Melanie Olsen, Bouchra Senadji, Mostafa Rahimi Azghadi

机构 * College of Science and Engineering, James Cook University（詹姆斯库克大学科学与工程学院） ； The Australian Institute of Marine Science（澳大利亚海洋科学研究所） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments 18 pages, 6 figures, 8 tables. Submitted to Elsevier

SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations

Songchun Zhang, Huiyao Xu, Sitong Guo, Zhongwei Xie, Hujun Bao, Weiwei Xu, Changqing Zou

机构 * ZJU（浙江大学） ； HKUST（香港科技大学） ； Zhejiang Lab（浙江实验室） 纠错

专题命中 三维重建 ：novel view synthesis(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025. 12 pages, 9 figures

FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video

Yue Gao, Hong-Xing Yu, Bo Zhu, Jiajun Wu

机构 * Stanford University（斯坦福大学） ； Microsoft（微软公司） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

专题命中 三维重建 ：novel view synthesis(abstract)；分类 cs.CV

Comments CVPR 2025 (oral). The first two authors contributed equally. Project website: https://yuegao.me/FluidNexus

Hierarchical Reinforcement Learning for Articulated Tool Manipulation with Multifingered Hand

Wei Xu, Yanchao Zhao, Weichao Guo, Xinjun Sheng

机构 * State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University（机械系统与振动国家重点实验室，机械工程学院，上海交通大学） ； Shanghai Key Laboratory of Intelligent Robotics, Meta Robotics Institute, Shanghai Jiao Tong University（智能机器人上海重点实验室，元机器人研究院，上海交通大学） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.RO

Comments Accepted by 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025). copyright 2025 IEEE. Final version to appear in IEEE Xplore

BVI-CR: A Multi-View Human Dataset for Volumetric Video Compression

Ge Gao, Adrian Azzarelli, Ho Man Kwan, Nantheera Anantrasirichai, Fan Zhang, Oliver Moolan-Feroze, David Bull

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Hierarchical Procedural Framework for Low-latency Robot-Assisted Hand-Object Interaction

Mingqi Yuan, Huijiang Wang, Kai-Fung Chu, Fumiya Iida, Bo Li, Wenjun Zeng

机构 * Bio-Inspired Robotics Lab, Department of Engineering, University of Cambridge（剑桥大学工程系生物启发机器人实验室） ； Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系） ； Eastern Institute of Technology, Ningbo, Zhejiang（宁波工程技术学院） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.RO

Comments 6 pages, 5 figures

Journal ref 2025 IEEE International Conference on Systems, Man, and Cybernetics

Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Room

Tony Danjun Wang, Lennart Bastian, Tobias Czempiel, Christian Heiliger, Nassir Navab

机构 * Chair for Computer Aided Medical Procedures, Technical University of Munich（计算机辅助医疗程序研究所，慕尼黑技术大学） ； UCL Hawkes Institute, Dept. Computer Science, University College London（UCL哈维斯研究所，伦敦大学学院计算机科学系） ； Department of General, Visceral, and Transplant Surgery, University Hospital, Ludwig-Maximilians-University（普通外科、 visceral外科及移植外科部门，路德维希-马克西米利安大学医院） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.CV

Comments 26 pages, 14 figures

Journal ref Medical Image Analysis, vol. 105, p. 103687 (2025)

3D Heart Reconstruction from Sparse Pose-agnostic 2D Echocardiographic Slices

Zhurong Chen, Jinhua Chen, Wei Zhuo, Wufeng Xue, Dong Ni

机构 * Shenzhen University, Shenzhen, China（深圳大学，深圳，中国） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments 10 pages

Modular Soft Wearable Glove for Real-Time Gesture Recognition and Dynamic 3D Shape Reconstruction

Huazhi Dong, Chunpeng Wang, Mingyuan Jiang, Francesco Giorgio-Serchi, Yunjie Yang

机构 * SMART Group, Institute for Imaging, Data and Communications, The University of Edinburgh（SMART集团，成像、数据与通信研究所，爱丁堡大学） ； Institute for Integrated Micro and Nano Systems, The University of Edinburgh（集成微纳系统研究所，爱丁堡大学） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.RO

MVGBench: Comprehensive Benchmark for Multi-view Generation Models

Xianghui Xie, Chuhang Zou, Meher Gitika Karumuri, Jan Eric Lenssen, Gerard Pons-Moll

机构 * University of Tübingen（图宾根大学） ； Tübingen AI Center（图宾根人工智能中心） ； Max Planck Institute for Informatics（马克斯·普朗克信息研究所） ； Independent researcher（独立研究者） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.GR

Comments 17 pages, 11 figures, 9 tables, project page: https://virtualhumans.mpi-inf.mpg.de/MVGBench/

GeoCD: A Differential Local Approximation for Geodesic Chamfer Distance

Pedro Alonso, Tianrui Li, Chongshou Li

机构 * School of Computing and Artificial Intelligence, Southwest Jiaotong University（计算机与人工智能学院，西南交通大学） ； Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education, Chengdu, China（可持续城市智能交通工程研究中心，教育部，成都，中国） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.CV

VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions

Marko Mihajlovic, Siwei Zhang, Gen Li, Kaifeng Zhao, Lea Müller, Siyu Tang

机构 * ETH Zürich（苏黎世联邦理工学院） ； UC Berkeley（伯克利大学） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.CV

Comments [ICCV 2025] https://markomih.github.io/VolumetricSMPL

Coordinated 2D-3D Visualization of Volumetric Medical Data in XR with Multimodal Interactions

Qixuan Liu, Shi Qiu, Yinqiao Wang, Xiwen Wu, Kenneth Siu Ho Chok, Chi-Wing Fu, Pheng-Ann Heng

专题命中 三维重建 ：spatial understanding(abstract)；分类 cs.GR

Comments IEEE VIS 2025 Short Paper

DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion

Yansong Qu, Shaohui Dai, Xinyang Li, Yuze Wang, You Shen, Liujuan Cao, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室、厦门大学） ； State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（虚拟现实技术与系统国家重点实验室、北京航空航天大学） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments Project page: \url{https://quyans.github.io/DeOcc123/}

Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning

Remco F. Leijenaar, Hamidreza Kasaei

机构 * Department of AI, University of Groningen（人工智能系，格罗宁根大学） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.CV

Comments for associated source code, see https://github.com/RFLeijenaar/AsymDSD

PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors

Sai Sri Teja, Sreevidya Chintalapati, Vinayak Gupta, Mukund Varma T, Haejoon Lee, Aswin Sankaranarayanan, Kaushik Mitra

机构 * Department of Electrical Engineering, Indian Institute of Technology, Madras, India（电子工程系，印度理工学院Madras分校） ； Department of Computer Science, University of California, San Diego, CA 92093（计算机科学系，加州大学圣地亚哥分校） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments Accepted at the International Conference on Computational Photography(ICCP) 2025

Online camera-pose-free stereo endoscopic tissue deformation recovery with tissue-invariant vision-biomechanics consistency

Jiahe Chen, Naoki Tomii, Ichiro Sakuma, Etsuko Kobayashi

机构 * School of Engineering, The University of Tokyo（东京大学工学系） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

The MOTIF Hand: A Robotic Hand for Multimodal Observations with Thermal, Inertial, and Force Sensors

Hanyang Zhou, Haozhe Lou, Wenhao Liu, Enyu Zhao, Yue Wang, Daniel Seita

机构 * Department of Computer Science, Viterbi School of Engineering University of Southern California（计算机科学系，维特比工程学院，南加州大学） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.RO

Mobile Image Analysis Application for Mantoux Skin Test

Liong Gele, Tan Chye Cheah

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation

Chaoyang Wang, Ashkan Mirzaei, Vidit Goel, Willi Menapace, Aliaksandr Siarohin, Avalon Vinella, Michael Vasilkovsky, Ivan Skorokhodov, Vladislav Shakhrai, Sergey Korolev, Sergey Tulyakov, Peter Wonka

机构 * Snap Inc. ； KAUST 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

PhysID: Physics-based Interactive Dynamics from a Single-view Image

Sourabh Vasant Gothe, Ayon Chattopadhyay, Gunturi Venkata Sai Phani Kiran, Pratik, Vibhav Agarwal, Jayesh Rajkumar Vachhani, Sourav Ghosh, Parameswaranath VM, Barath Raj KR

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments Published in 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Project page: https://physid.github.io/

Journal ref 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5

Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion

Wang Zhao, Yan-Pei Cao, Jiale Xu, Yuejiang Dong, Ying Shan

机构 * Tencent ARC Lab（腾讯ARC实验室） ； Tsinghua University（清华大学） 纠错

专题命中 三维重建 ：point cloud(abstract)；分类 cs.CV

Comments Technical Report. Project page: https://assembler3d.github.io

Implicit 3D scene reconstruction using deep learning towards efficient collision understanding in autonomous driving

Akarshani Ramanayake, Nihal Kodikara

机构 * School of Computing（计算学院） ； Informatics Institute of Technology（信息技术研究所） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Plug-and-Play with 2.5D Artifact Reduction Prior for Fast and Accurate Industrial Computed Tomography Reconstruction

Haley Duba-Sullivan, Aniket Pramanik, Venkatakrishnan Singanallur, Amirkoushyar Ziabari

机构 * Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments Submitted to Journal of Nondestructive Evaluation

Test3R: Learning to Reconstruct 3D at Test Time

Yuheng Yuan, Qiuhong Shen, Shizun Wang, Xingyi Yang, Xinchao Wang

机构 * National University of Singapore（新加坡国立大学） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data

Vasiliki Balaska, Ioannis Tsampikos Papapetros, Katerina Maria Oikonomou, Loukas Bampis, Antonios Gasteratos

机构 * Department of Production and Management Engineering, Democritus University of Thrace（生产与管理工程系，德米特里乌斯·特拉基斯大学） ； Department of Electrical and Computer Engineering, Democritus University of Thrace（电气与计算机工程系，德米特里乌斯·特拉基斯大学） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.RO

SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction

Wenhao Shen, Gangjian Zhang, Jianfeng Zhang, Yu Feng, Nanjie Yao, Xuanmeng Zhang, Hao Wang

机构 * Nanyang Technological University（南洋理工大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； National University of Singapore（国立新加坡大学） ； Zhejiang University of Technology（浙江工业大学） ； University of Technology Sydney（悉尼大学） 纠错

专题命中 三维重建 ：3D reconstruction(abstract)；分类 cs.CV

Comments Accepted to ICME 2025 (Oral)