3D 视觉

2509.05776 2025-09-09 cs.CV 74%

Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models

Jonathan Aellen, Florian Burkhardt, Thomas Vetter, Marcel Lüthi

机构 * Department of Mathematics and Computer Science（数学与计算机科学系）； University of Basel（巴塞尔大学）

专题命中三维重建：3D reconstruction(title)；分类 cs.CV

2509.06672 2025-09-09 eess.SP 50%

ISAC Imaging by Channel State Information using Ray Tracing for Next Generation 6G

Ahmad Bazzi, Mingjun Ying, Ojas Kanhere, Theodore S. Rappaport, Marwa Chafii

专题命中三维重建：point cloud(abstract)

2509.05541 2025-09-09 stat.ML cs.LG cs.NA math.NA math.OC physics.data-an 50%

Cryo-EM as a Stochastic Inverse Problem

Diego Sanchez Espinosa, Erik H Thiede, Yunan Yang

机构 * Center for Applied Mathematics, Cornell University（应用数学中心，康奈尔大学）； Department of Chemistry, Cornell University（化学系，康奈尔大学）； Department of Mathematics, Cornell University（数学系，康奈尔大学）

专题命中三维重建：3D reconstruction(abstract)

Comments 25 pages, 8 figures

2508.20526 2025-09-09 cs.CV 85%

Adam SLAM - the last mile of camera calibration with 3DGS

Matthieu Gendrin, Stéphane Pateux, Xiaoran Jiang, Théo Ladune, Luce Morin

机构 * Orange Innovation（Orange创新）； Univ Rennes（里昂大学）； INSA Rennes（里昂国立应用科学学院）； CNRS（国家科学研究中心）； IETR (UMR 6164)（信息与通信技术研究所）

专题命中 Gaussian Splatting ：3DGS(title,abstract)；NeRF(abstract)；novel view synthesis(abstract)；分类 cs.CV

Journal ref ORASIS 2025, ISEN Yncréa Ouest, Jun 2025, Le Croisic, France. hal-05131219

2410.17505 2025-09-09 cs.CV 85%

PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting

Yu Wang, Xiaobao Wei, Ming Lu, Guoliang Kang

机构 * School of Automation Science and Electrical Engineering, Beihang University（北京航空航天大学自动化科学与电气工程学院）； Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences（中国科学院软件研究所）； Peking University（北京大学）

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)；NeRF(abstract)；3DGS(abstract)；分类 cs.CV

2509.06400 2025-09-09 cs.CV 83%

3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom

Matthieu Gendrin, Stéphane Pateux, Théo Ladune

机构 * Orange Innovation（奥兰奇创新）

专题命中 Gaussian Splatting ：3DGS(title,abstract)；Gaussian Splatting(abstract)；分类 cs.CV

Journal ref CORESA - COmpression et REprésentation des Signaux Audiovisuels, Institut National des Sciences Appliquées - Rennes [INSA Rennes], Nov 2024, Rennes, France

2408.10906 2025-09-09 cs.CV 77%

ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining

Qi Ma, Yue Li, Bin Ren, Nicu Sebe, Ender Konukoglu, Theo Gevers, Luc Van Gool, Danda Pani Paudel

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；3DGS(abstract)；point cloud(abstract)；分类 cs.CV

Comments Accepted as 3DV'25 Oral, project page: https://unique1i.github.io/ShapeSplat_webpage/

2508.11854 2025-09-09 cs.CV cs.LG 70%

ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages

Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haorang Wang, Matthew Lau, Wenke Lee, Wilian Lunardi, Martin Andreoni, Duen Horng Chau

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；3DGS(abstract)；分类 cs.CV

Comments 7 pages, 6 figures

2509.06456 2025-09-09 cs.CV 83%

Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark

Zongyi Xu, Zhongpeng Lang, Yilong Chen, Shanshan Zhao, Xiaoshui Huang, Yifan Zuo, Yan Zhang, Qianni Zhang, Xinbo Gao

专题命中点云：point cloud(title,abstract)；3D vision(abstract)；分类 cs.CV

2509.05954 2025-09-09 cs.CV 79%

StripDet: Strip Attention-Based Lightweight 3D Object Detection from Point Cloud

Weichao Wang, Wendong Mao, Zhongfeng Wang

机构 * School of Integrated Circuits, Shenzhen Campus of Sun Yat-sen University（中山大学集成电路学院，深圳校区）

专题命中点云：point cloud(title,abstract)；分类 cs.CV

2507.16743 2025-09-09 cs.CV 79%

Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption

Keneni W. Tesema, Lyndon Hill, Mark W. Jones, Gary K. L. Tam

机构 * Swansea University（斯旺西大学）

专题命中点云：point cloud(title,abstract)；分类 cs.CV

Comments Accepted for Computers and Graphics and EG Symposium on 3D Object Retrieval 2025 (3DOR'25)

2509.06506 2025-09-09 eess.SP 78%

Synesthesia of Machines (SoM)-Aided LiDAR Point Cloud Transmission for Collaborative Perception

Ensong Liu, Rongqing Zhang, Xiang Cheng, Jian Tang

专题命中点云：point cloud(title,abstract)

2509.06953 2025-09-09 cs.RO cs.AI cs.CV cs.LG cs.SY eess.SY 62%

Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments

Jiahui Yang, Jason Jingzhou Liu, Yulong Li, Youssef Khaky, Kenneth Shaw, Deepak Pathak

机构 * Carnegie Mellon University（卡内基梅隆大学）

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Website at \url{deep-reactive-policy.com}

2310.16788 2025-09-09 cs.CV cs.LG cs.RO 62%

The GOOSE Dataset for Perception in Unstructured Environments

Peter Mortimer, Raphael Hagmanns, Miguel Granero, Thorsten Luettel, Janko Petereit, Hans-Joachim Wuensche

机构 * Institute for Autonomous Systems Technology, University of the Bundeswehr Munich（Bundeswehr Munich大学自主系统技术研究所）； Fraunhofer Institute of Optronics, System Technologies and Image Exploitation（弗劳恩霍夫光学与系统技术及图像利用研究所）； Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄技术大学）

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted at ICRA 2024, Github link: https://github.com/FraunhoferIOSB/goose_dataset

2509.06705 2025-09-09 cs.CV 57%

Cortex-Synth: Differentiable Topology-Aware 3D Skeleton Synthesis with Hierarchical Graph Attention

Mohamed Zayaan S

机构 * Department of Civil Engineering（土木工程系）； Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 8 pages, 4 figures

2509.06329 2025-09-09 cs.CV q-bio.QM 57%

Towards scalable organ level 3D plant segmentation: Bridging the data algorithm computing gap

Ruiming Du, Guangxun Zhai, Tian Qiu, Yu Jiang

机构 * Department of Biological and Environmental Engineering（生物与环境工程系）； Horticulture Section, School of Integrative Plant Science（植物科学整合学院园艺系）； School of Electrical and Computer Engineering（电气与计算机工程学院）

专题命中点云：point cloud(abstract)；分类 cs.CV

2508.17230 2025-09-09 cs.CV 57%

4D Visual Pre-training for Robot Learning

Chengkai Hou, Yanjie Ze, Yankai Fu, Zeyu Gao, Songbo Hu, Yue Yu, Shanghang Zhang, Huazhe Xu

机构 * Peking University（北京大学）； Tsinghua University（清华大学）； Shanghai Qizhi Institute（上海启智研究院）； CASIA（中国科学院自动化研究所）； Shanghai AI Lab（上海人工智能实验室）

专题命中点云：point cloud(abstract)；分类 cs.CV

2409.10925 2025-09-09 cs.CV 83%

HGSLoc: 3DGS-based Heuristic Camera Pose Refinement

Zhongyan Niu, Zhen Tan, Jinpu Zhang, Xueliang Yang, Dewen Hu

机构 * the College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学）

专题命中新视角合成：3DGS(title)；NeRF(abstract)；3D reconstruction(abstract)；分类 cs.CV

Journal ref Proc. IEEE International Conference on Robotics and Automation (ICRA), 2025

2509.06950 2025-09-09 cs.GR cs.CV 81%

Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data

Nithin Gopalakrishnan Nair, Srinivas Kaza, Xuan Luo, Vishal M. Patel, Stephen Lombardi, Jungyeon Park

机构 * Johns Hopkins University（约翰霍普金斯大学）； Google（谷歌公司）

专题命中新视角合成：novel view synthesis(title,abstract)；分类 cs.CV、cs.GR

Comments Accepted at ICCV 2025

2509.06579 2025-09-09 cs.CV 79%

CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis

Xin Kong, Daniel Watson, Yannick Strümpler, Michael Niemeyer, Federico Tombari

机构 * Imperial College London（伦敦帝国学院）； Google DeepMind（谷歌DeepMind）； Google（谷歌）； Technical University of Munich（慕尼黑技术大学）

专题命中新视角合成：novel view synthesis(title,abstract)；分类 cs.CV

2509.06798 2025-09-09 cs.CV 57%

SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis

Zhengqing Chen, Ruohong Mei, Xiaoyang Guo, Qingjie Wang, Yubin Hu, Wei Yin, Weiqiang Ren, Qian Zhang

机构 * Horizon Robotics ； Tsinghua University（清华大学）

专题命中 3D生成：3D generation(abstract)；分类 cs.CV

Comments 8 pages

2503.13111 2025-09-09 cs.CV cs.CL cs.LG 79%

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs

Erik Daxberger, Nina Wenzel, David Griffiths, Haiming Gang, Justin Lazarow, Gefen Kohavi, Kai Kang, Marcin Eichner, Yinfei Yang, Afshin Dehghan, Peter Grasch

机构 * Apple（苹果公司）

专题命中空间理解：spatial understanding(title,abstract)；分类 cs.CV

Comments ICCV 2025

2509.05578 2025-09-09 cs.AI cs.RO 70%

OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision

Ruixun Liu, Lingyu Kong, Derun Li, Hang Zhao

机构 * Shanghai Qi Zhi Institute（上海启智研究所）； Xi’an Jiaotong University（西安交通大学）； Fudan University（复旦大学）； Shanghai Jiao Tong University（上海交通大学）； Tsinghua University（清华大学）

专题命中空间理解：3D vision(abstract)；spatial understanding(abstract)；分类 cs.RO

2509.06233 2025-09-09 cs.RO cs.CV 62%

O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation

Tongxuan Tian, Xuhui Kang, Yen-Ling Kuo

机构 * University of Virginia（弗吉尼亚大学）

专题命中空间理解：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Conference on Robot Learning (CoRL) 2025. Project website: https://o3afford.github.io/

2503.09423 2025-09-09 cs.RO cs.CV 62%

Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter

Kechun Xu, Xunlong Xia, Kaixuan Wang, Yifei Yang, Yunxuan Mao, Bing Deng, Jieping Ye, Rong Xiong, Yue Wang

机构 * Zhejiang University and Alibaba Cloud（浙江大学和阿里云）； Alibaba Cloud（阿里云）； Zhejiang University（浙江大学）

专题命中其他3D视觉：3D vision(abstract)；分类 cs.CV、cs.RO

Comments Accepted by T-ASE and CoRL25 GenPriors Workshop

1. 三维重建 3 篇

Posterior shape models revisited: Improving 3D reconstructions from partial data using target specific models

ISAC Imaging by Channel State Information using Ray Tracing for Next Generation 6G

Cryo-EM as a Stochastic Inverse Problem

2. Gaussian Splatting 5 篇

Adam SLAM - the last mile of camera calibration with 3DGS

PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting

3DOF+Quantization: 3DGS quantization for large scenes with limited Degrees of Freedom

ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining

ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages

3. 点云 9 篇

Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark

StripDet: Strip Attention-Based Lightweight 3D Object Detection from Point Cloud

Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption

Synesthesia of Machines (SoM)-Aided LiDAR Point Cloud Transmission for Collaborative Perception

Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments

The GOOSE Dataset for Perception in Unstructured Environments

Cortex-Synth: Differentiable Topology-Aware 3D Skeleton Synthesis with Hierarchical Graph Attention

Towards scalable organ level 3D plant segmentation: Bridging the data algorithm computing gap

4D Visual Pre-training for Robot Learning

4. 新视角合成 3 篇

HGSLoc: 3DGS-based Heuristic Camera Pose Refinement

Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data

CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis

5. 3D生成 1 篇

SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis

6. 空间理解 3 篇

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs

OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision

O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation

7. 其他3D视觉 1 篇

Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter