3D 视觉 - arXivDaily 专题

2509.09143 2025-09-12 cs.CV cs.AI cs.GR 62%

Objectness Similarity: Capturing Object-Level Fidelity in 3D Scene Evaluation

Yuiko Uchida, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama

机构 * Hokkaido University（北海道大学）

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

Comments Accepted by the ICCV 2025 UniLight Workshop

2508.19508 2025-08-28 cs.RO cs.CV 62%

DATR: Diffusion-based 3D Apple Tree Reconstruction Framework with Sparse-View

Tian Qiu, Alan Zoubi, Yiyuan Lin, Ruiming Du, Lailiang Cheng, Yu Jiang

机构 * School of Electrical and Computer Engineering, Cornell University（电气与计算机工程系，康奈尔大学）； Sibley School of Mechanical and Aerospace Engineering, Cornell University（机械与航空航天工程系，康奈尔大学）； School of Biological and Environmental Engineering, Cornell University（生物与环境工程系，康奈尔大学）； School of Integrative Plant Science, Cornell University（整合植物科学系，康奈尔大学）

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

2508.14892 2025-08-21 cs.GR cs.CV 62%

Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

Jia Lu, Taoran Yi, Jiemin Fang, Chen Yang, Chuiyun Wu, Wei Shen, Wenyu Liu, Qi Tian, Xinggang Wang

机构 * Huazhong University of Science and Technology（华中科技大学）； Huawei Inc.（华为公司）； Shanghai Jiaotong University（上海交通大学）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments Project page: https://hustvl.github.io/Snap-Snap/

2508.13228 2025-08-20 cs.GR cs.AI cs.CV eess.IV 62%

PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism

Yuyan Ye, Hang Xu, Yanghang Huang, Jiali Huang, Qian Weng

机构 * College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China（计算机与数据科学学院，福州大学，福州350108，中国）

专题命中三维重建：NeRF(abstract)；分类 cs.CV、cs.GR

Comments 2025 International Joint Conference on Neural Networks (IJCNN 2025)

2508.08086 2025-08-12 cs.CV cs.GR 62%

Matrix-3D: Omnidirectional Explorable 3D World Generation

Zhongqi Yang, Wenhang Ge, Yuqi Li, Jiaqi Chen, Haoyuan Li, Mengyin An, Fei Kang, Hua Xue, Baixin Xu, Yuyang Yin, Eric Li, Yang Liu, Yikai Wang, Hao-Xiang Guo, Yahui Zhou

机构 * Skywork AI ； Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）

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

Comments Technical Report

2505.17966 2025-08-12 cs.RO cs.CV 62%

Is Single-View Mesh Reconstruction Ready for Robotics?

Frederik Nolte, Andreas Geiger, Bernhard Schölkopf, Ingmar Posner

机构 * Oxford Robotics Institute, University of Oxford（牛津大学机器人研究所）； University of Tübingen（图宾根大学）； Max Planck Institute for Intelligent Systems & ELLIS Institute Tübingen（马克斯·普朗克智能系统研究所及图宾根ELLIS研究所）

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

Comments 20 pages, 18 figures

2507.12714 2025-08-08 cs.CV cs.GR 62%

NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement

Yang Yang, Dongni Mao, Hiroaki Santo, Yasuyuki Matsushita, Fumio Okura

机构 * The University of Osaka（大阪大学）； Microsoft Research Asia – Tokyo（微软亚洲研究院-东京）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments IEEE/CVF International Conference on Computer Vision (ICCV 2025), Highlight, Project: https://neuraleaf-yang.github.io/

2508.04508 2025-08-07 cs.GR cs.CV 62%

Surf3R: Rapid Surface Reconstruction from Sparse RGB Views in Seconds

Haodong Zhu, Changbai Li, Yangyang Ren, Zichao Feng, Xuhui Liu, Hanlin Chen, Xiantong Zhen, Baochang Zhang

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

2503.10624 2025-08-06 cs.CV cs.AI cs.GR 62%

ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness

Boqian Li, Haiwen Feng, Zeyu Cai, Michael J. Black, Yuliang Xiu

机构 * Westlake University（西湖大学）； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）； UC Berkeley（加州大学伯克利分校）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments Page: https://boqian-li.github.io/ETCH/, Code: https://github.com/boqian-li/ETCH

2411.17489 2025-07-30 cs.CV cs.AI cs.GR cs.LG 62%

Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions

Nicolai Hermann, Jorge Condor, Piotr Didyk

机构 * USI（USI大学）； IDSIA（IDSIA研究所）

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

2210.00541 2025-07-28 cs.CV cs.RO 62%

Semi-autonomous Prosthesis Control Using Minimal Depth Information and Vibrotactile Feedback

Miguel Nobre Castro, Strahinja Dosen

机构 * Neurorehabilitation Systems Research Group, Department of Health Science and Technology, Faculty of Medicine, Aalborg University（神经康复系统研究组，健康科学与技术系，医学学院，奥胡斯大学）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.RO

2507.14624 2025-07-22 cs.GR cs.CV 62%

Real-Time Scene Reconstruction using Light Field Probes

Yaru Liu, Derek Nowrouzezahri, Morgan Mcguire

机构 * University of Cambridge（剑桥大学）； McGill University（麦吉尔大学）

专题命中三维重建：novel view synthesis(abstract)；分类 cs.CV、cs.GR

2507.13857 2025-07-21 cs.CV cs.RO 62%

Depth3DLane: Fusing Monocular 3D Lane Detection with Self-Supervised Monocular Depth Estimation

Max van den Hoven, Kishaan Jeeveswaran, Pieter Piscaer, Thijs Wensveen, Elahe Arani, Bahram Zonooz

机构 * Eindhoven University of Technology（埃因霍温理工大学）； TNO（荷兰国防研究院）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.RO

2507.08726 2025-07-14 cs.RO cs.CV 62%

Learning human-to-robot handovers through 3D scene reconstruction

Yuekun Wu, Yik Lung Pang, Andrea Cavallaro, Changjae Oh

机构 * Centre for Intelligent Sensing, Queen Mary University of London（智能感知中心，伦敦女王玛丽大学）； Idiap Research Institute and École Polytechnique Fédérale de Lausanne（Idiap研究机构和瑞士洛桑联邦理工学院）

专题命中三维重建：Gaussian Splatting(abstract)；分类 cs.CV、cs.RO

Comments 8 pages, 6 figures, 2 table

2507.07465 2025-07-11 cs.GR cs.CV 62%

SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction

Wei Yao, Shuzhao Xie, Letian Li, Weixiang Zhang, Zhixin Lai, Shiqi Dai, Ke Zhang, Zhi Wang

机构 * SIGS, Tsinghua University（清华大学信号与信息处理系）； Google（谷歌）； Department of CST, Tsinghua University（清华大学计算机科学与技术系）； Soochow University（苏州大学）

专题命中三维重建：Gaussian Splatting(abstract)；分类 cs.CV、cs.GR

2507.05627 2025-07-09 cs.RO cs.CV 62%

DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation

Young Hun Kim, Seungyeon Kim, Yonghyeon Lee, Frank Chongwoo Park

机构 * Seoul National University（首尔国立大学）； Massachusetts Institute of Technology（麻省理工学院）

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

2507.05304 2025-07-09 cs.GR cs.AI cs.CV 62%

Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshes

Saqib Nazir, Olivier Lézoray, Sébastien Bougleux

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Journal ref International Joint Conference on Neural Networks, Jun 2025, Rome, Italy

2412.16776 2025-07-08 cs.CV cs.GR cs.LG 62%

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

Sanghyun Son, Matheus Gadelha, Yang Zhou, Matthew Fisher, Zexiang Xu, Yi-Ling Qiao, Ming C. Lin, Yi Zhou

机构 * University of Maryland（马里兰大学）； Adobe Research（Adobe研究）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments 20 pages, 24 figures, 6 tables

2412.10444 2025-07-08 cs.CV cs.RO 62%

Boundary Exploration of Next Best View Policy in 3D Robotic Scanning

Leihui Li, Lixuepiao Wan, Xuping Zhang

机构 * Department of Mechanical and Production Engineering, Aarhus University（机械与生产工程系，阿arhus大学）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.RO

2404.13445 2025-07-08 cs.CV cs.GR 62%

DMesh: A Differentiable Mesh Representation

Sanghyun Son, Matheus Gadelha, Yang Zhou, Zexiang Xu, Ming C. Lin, Yi Zhou

机构 * University of Maryland, College Park（马里兰大学学院公园分校）； Adobe Research（Adobe研究）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments 36 pages, 24 figures. Updated with camera-ready version

2406.18582 2025-06-27 cs.CV cs.GR 62%

CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequences

Miaowei Wang, Changjian Li, Amir Vaxman

机构 * University of Edinburgh（爱丁堡大学）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments ICCV2025 Accepted

2506.18017 2025-06-24 cs.GR cs.AI cs.CV 62%

Auto-Regressive Surface Cutting

Yang Li, Victor Cheung, Xinhai Liu, Yuguang Chen, Zhongjin Luo, Biwen Lei, Haohan Weng, Zibo Zhao, Jingwei Huang, Zhuo Chen, Chunchao Guo

机构 * Tencent Hunyuan（腾讯文言）； SYSU（华南理工大学）； CUHKSZ（香港中文大学）； SCUT（华南理工大学）； ShanghaiTech（上海交通大学）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments Tech. report. https://victorcheung12.github.io/seamgpt

2503.12553 2025-06-18 cs.GR cs.CV 62%

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View

Xianzu Wu, Zhenxin Ai, Harry Yang, Ser-Nam Lim, Jun Liu, Huan Wang

机构 * Xianzu Wu（无）； Zhenxin Ai（无）； Harry Yang（无）； Sernam Lim（无）； Jun Liu（无）； Huan Wang（无）

专题命中三维重建：novel view synthesis(abstract)；分类 cs.CV、cs.GR

2408.14732 2025-06-10 cs.CV cs.GR 62%

OctFusion: Octree-based Diffusion Models for 3D Shape Generation

Bojun Xiong, Si-Tong Wei, Xin-Yang Zheng, Yan-Pei Cao, Zhouhui Lian, Peng-Shuai Wang

机构 * Peking University（北京大学）； Tsinghua University（清华大学）； VAST（中国科学院软件研究所）

专题命中三维重建：3D generation(abstract)；分类 cs.CV、cs.GR

Comments Accepted to Computer Graphics Forum (SGP), 2025

2506.04444 2025-06-06 cs.CV cs.AI cs.GR cs.HC cs.MM 62%

Photoreal Scene Reconstruction from an Egocentric Device

Zhaoyang Lv, Maurizio Monge, Ka Chen, Yufeng Zhu, Michael Goesele, Jakob Engel, Zhao Dong, Richard Newcombe

机构 * Reality Labs Research, Meta（Meta现实实验室研究）

专题命中三维重建：Gaussian Splatting(abstract)；分类 cs.CV、cs.GR

Comments Paper accepted to SIGGRAPH Conference Paper 2025

2503.19136 2025-06-06 cs.GR cs.CV cs.LG stat.ML 62%

Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Sidhanth Holalkere, David S. Bindel, Silvia Sellán, Alexander Terenin

机构 * cornell（康奈尔大学）； mit（麻省理工学院）； columbia（哥伦比亚大学）

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Journal ref International Conference on Machine Learning, 2025

2405.14979 2025-06-02 cs.GR cs.CV 62%

CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner

Weiyu Li, Jiarui Liu, Hongyu Yan, Rui Chen, Yixun Liang, Xuelin Chen, Ping Tan, Xiaoxiao Long

机构 * HKUST（香港科技大学）； LightIllusions ； Adobe Research（Adobe研究院）

专题命中三维重建：3D generation(abstract)；分类 cs.CV、cs.GR

Comments HomePage: https://craftsman3d.github.io/, Code: https://github.com/wyysf-98/CraftsMan3D

2405.05648 2025-05-27 cs.RO cs.CV 62%

ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera

Jun Shi, Yong A, Yixiang Jin, Dingzhe Li, Haoyu Niu, Zhezhu Jin, He Wang

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.RO

Comments IEEE International Conference on Robotics and Automation (ICRA), 2024

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2024, pp. 5441-5447

2505.15373 2025-05-22 cs.CV cs.RO 62%

RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation

Naman Patel, Prashanth Krishnamurthy, Farshad Khorrami

机构 * Control/Robotics Research Laboratory (CRRL), Department of Electrical and Computer Engineering, NYU Tandon School of Engineering（控制/机器人研究实验室（CRRL），电气与计算机工程系，纽约大学Tandon工程学院）

专题命中三维重建：spatial understanding(abstract)；分类 cs.CV、cs.RO

2504.14257 2025-05-13 cs.GR cs.CV 62%

HoLa: B-Rep Generation using a Holistic Latent Representation

Yilin Liu, Duoteng Xu, Xingyao Yu, Xiang Xu, Daniel Cohen-Or, Hao Zhang, Hui Huang

专题命中三维重建：point cloud(abstract)；分类 cs.CV、cs.GR

Comments ACM TOG and SIGGRAPH 2025 (Patent Protected); Project page: https://vcc.tech/research/2025/HolaBrep; Demo page: https://huggingface.co/spaces/YuXingyao/HoLa-BRep

1. 三维重建 4393 篇

Objectness Similarity: Capturing Object-Level Fidelity in 3D Scene Evaluation

DATR: Diffusion-based 3D Apple Tree Reconstruction Framework with Sparse-View

Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism

Matrix-3D: Omnidirectional Explorable 3D World Generation

Is Single-View Mesh Reconstruction Ready for Robotics?

NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement

Surf3R: Rapid Surface Reconstruction from Sparse RGB Views in Seconds

ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness

Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions

Semi-autonomous Prosthesis Control Using Minimal Depth Information and Vibrotactile Feedback

Real-Time Scene Reconstruction using Light Field Probes

Depth3DLane: Fusing Monocular 3D Lane Detection with Self-Supervised Monocular Depth Estimation

Learning human-to-robot handovers through 3D scene reconstruction

SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction

DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation

Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshes

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

Boundary Exploration of Next Best View Policy in 3D Robotic Scanning

DMesh: A Differentiable Mesh Representation

CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequences

Auto-Regressive Surface Cutting

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View

OctFusion: Octree-based Diffusion Models for 3D Shape Generation

Photoreal Scene Reconstruction from an Egocentric Device

Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner

ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera

RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation

HoLa: B-Rep Generation using a Holistic Latent Representation