3D 视觉 - arXivDaily 专题

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

2505.04590 2025-05-09 cs.GR cs.CV 62%

TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization

Alexandre Binninger, Ruben Wiersma, Philipp Herholz, Olga Sorkine-Hornung

机构 * ETH Zurich（苏黎世联邦理工学院）

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

Comments ACM Trans. Graph. 44, 4. SIGGRAPH 2025. 19 pages, 21 figures

2504.19174 2025-05-06 cs.GR cs.CV 62%

CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation

Xueqi Ma, Yilin Liu, Tianlong Gao, Qirui Huang, Hui Huang

机构 * College of Computer Science & Software Engineering（计算机科学与软件工程学院）； Shenzhen University（深圳大学）

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

Comments ACM SIGGRAPH 2025 (Patent Protected); Project page: https://vcc.tech/research/2025/CLRWire

2406.04861 2025-04-23 cs.CV cs.GR 62%

Normal-guided Detail-Preserving Neural Implicit Function for High-Fidelity 3D Surface Reconstruction

Aarya Patel, Hamid Laga, Ojaswa Sharma

机构 * Graphics Research Group, IIIT Delhi（IIIT德里图形研究组）； Murdoch University（默doch大学）； IIIT Delhi（IIIT德里）

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

Comments Accepted at ACM SIGGRAPH I3D 2025. Published in PACMCGIT journal. Project page with images and code: https://graphics-research-group.github.io/sn-nir

2504.13072 2025-04-18 cs.GR cs.CV cs.MM 62%

HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation

Wenqi Dong, Bangbang Yang, Zesong Yang, Yuan Li, Tao Hu, Hujun Bao, Yuewen Ma, Zhaopeng Cui

机构 * Zhejiang University（浙江大学）； ByteDance（字节跳动）

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

Comments Project webpage: https://zju3dv.github.io/hiscene/

2405.07847 2025-04-17 cs.CV cs.RO 62%

SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modeling

Yijun Yuan, Michael Bleier, Andreas Nüchter

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

Comments Accepted to IEEE Transactions on Robotics (T-RO). For project page and code, please find https://jarrome.github.io/SceneFactory/

2504.10857 2025-04-16 cs.RO cs.CV 62%

ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping

Shun Iwase, Zubair Irshad, Katherine Liu, Vitor Guizilini, Robert Lee, Takuya Ikeda, Ayako Amma, Koichi Nishiwaki, Kris Kitani, Rares Ambrus, Sergey Zakharov

机构 * Carnegie Mellon University（卡内基梅隆大学）； Toyota Research Institute（丰田研究所）； Woven by Toyota（丰田编织）

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

Comments Published at CVPR 2025, Webpage: https://sh8.io/#/zerograsp

2409.16294 2025-04-10 cs.CV cs.GR cs.LG 62%

GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priors

Md Ferdous Alam, Faez Ahmed

机构 * Massachusetts Institute of Technology（麻省理工学院）

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

Comments 24 pages, 13 figures

2410.09417 2025-04-09 cs.GR cs.CV 62%

Neurally Integrated Finite Elements for Differentiable Elasticity on Evolving Domains

Gilles Daviet, Tianchang Shen, Nicholas Sharp, David I. W. Levin

机构 * NVIDIA（英伟达）

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

Comments 18 pages, 24 figures

Journal ref ACM Transactions on Graphics 2025

2504.01901 2025-04-03 cs.CV cs.AI cs.CL cs.RO 62%

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

Haochen Wang, Yucheng Zhao, Tiancai Wang, Haoqiang Fan, Xiangyu Zhang, Zhaoxiang Zhang

机构 * Dexmal ； MEGVII Technology（旷视科技）； StepFun

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

2504.01027 2025-04-03 cs.GR cs.CV 62%

Mesh Compression with Quantized Neural Displacement Fields

Sai Karthikey Pentapati, Gregoire Phillips, Alan C. Bovik

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）； Ericsson Inc.（爱立信公司）

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

2411.16820 2025-04-02 cs.CV cs.GR 62%

DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow

Ken Deng, Yuan-Chen Guo, Jingxiang Sun, Zi-Xin Zou, Yangguang Li, Xin Cai, Yan-Pei Cao, Yebin Liu, Ding Liang

机构 * Tsinghua University（清华大学）； VAST ； Sun Yat-sen University（中山大学）； The Chinese University of Hong Kong（香港中文大学）

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

2503.21886 2025-03-31 cs.GR cs.CV 62%

Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video

Pilseo Park, Ze Zhang, Michel Sarkis, Ning Bi, Xiaoming Liu, Yiying Tong

机构 * Michigan State University（密歇根州立大学）； Qualcomm Technologies, Inc.（高通技术公司）

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

2412.15618 2025-03-26 cs.CV cs.GR 62%

3D Shape Tokenization via Latent Flow Matching

Jen-Hao Rick Chang, Yuyang Wang, Miguel Angel Bautista Martin, Jiatao Gu, Xiaoming Zhao, Josh Susskind, Oncel Tuzel

机构 * Apple（苹果公司）

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

2411.18335 2025-03-26 cs.CV cs.AI cs.RO 62%

Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation

Mehdi Zayene, Jannik Endres, Albias Havolli, Charles Corbière, Salim Cherkaoui, Alexandre Kontouli, Alexandre Alahi

机构 * EPFL（洛桑联邦理工学院）； TU Darmstadt（达姆施塔特工业大学）

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

Comments Accepted to CVPR 2025. Project page: https://vita-epfl.github.io/Helvipad

2412.08591 2025-03-20 cs.CV cs.AI cs.RO 62%

RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation

Mingfei Han, Liang Ma, Kamila Zhumakhanova, Ekaterina Radionova, Jingyi Zhang, Xiaojun Chang, Xiaodan Liang, Ivan Laptev

机构 * MBZUAI（默罕默德·本·扎耶德人工智能大学）； Shenzhen Campus of Sun Yat-Sen University（中山大学深圳校区）； AAII, UTS（悉尼科技大学人工智能与创新研究所）； University of Science and Technology of China（中国科学技术大学）

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

Comments CVPR2025

2503.11629 2025-03-17 cs.GR cs.CV cs.MM 62%

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

Stefan Lionar, Jiabin Liang, Gim Hee Lee

机构 * Sea AI Lab ； Garena ； National University of Singapore（新加坡国立大学）

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

Comments CVPR 2025. Code: https://github.com/sail-sg/TreeMeshGPT

2503.08166 2025-03-12 cs.GR cs.CV 62%

Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streaming

Jiaxuan Zhu, Hao Tang

机构 * School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）； School of Computer Science, Peking University（北京大学计算机学院）

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

Comments 20 pages, 6 figures

2403.15107 2025-03-10 cs.RO cs.CV 62%

PseudoTouch: Efficiently Imaging the Surface Feel of Objects for Robotic Manipulation

Adrian Röfer, Nick Heppert, Abdallah Ayad, Eugenio Chisari, Abhinav Valada

机构 * University of Freiburg（弗莱堡大学）； Zuse School ELIZA（楚塞ELIZA学院）

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

Comments 7 pages, 5 figures, 2 tables, accepted at ICRA 2025

2407.01888 2025-03-09 cs.RO cs.CV 62%

PO-MSCKF: An Efficient Visual-Inertial Odometry by Reconstructing the Multi-State Constrained Kalman Filter with the Pose-only Theory

Xueyu Du, Lilian Zhang, Ruochen Liu, Maosong Wang, Wenqi Wu, Jun Mao

机构 * College of Intelligent Science and Technology, National University of Defense Technology（国防科技大学智能科学学院）

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

2407.13304 2025-03-07 cs.CV cs.RO 62%

A Dataset and Benchmark for Shape Completion of Fruits for Agricultural Robotics

Federico Magistri, Thomas Läbe, Elias Marks, Sumanth Nagulavancha, Yue Pan, Claus Smitt, Lasse Klingbeil, Michael Halstead, Heiner Kuhlmann, Chris McCool, Jens Behley, Cyrill Stachniss

机构 * University of Bonn（波恩大学）； Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）； University of Oxford（牛津大学）

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

2503.02745 2025-03-06 cs.GR cs.CV cs.LG 62%

ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points

Qirui Huang, Runze Zhang, Kangjun Liu, Minglun Gong, Hao Zhang, Hui Huang

机构 * Shenzhen University（深圳大学）； Pengcheng Laboratory（鹏城实验室）； University of Guelph（圭尔夫大学）； Simon Fraser University（西蒙菲莎大学）

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

Comments CVPR 2025 (Patent Protected); Project page: https://vcc.tech/research/2025/ArcPro

2503.00625 2025-03-04 cs.MM cs.CV cs.GR 62%

Perceptual Visual Quality Assessment: Principles, Methods, and Future Directions

Wei Zhou, Hadi Amirpour, Christian Timmerer, Guangtao Zhai, Patrick Le Callet, Alan C. Bovik

机构 * Cardiff University（卡迪夫大学）； University of Klagenfurt（克拉根福大学）； Shanghai Jiao Tong University（上海交通大学）； University of Nantes（南特大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

Comments A tutorial and review

2502.09824 2025-02-17 cs.RO cs.CV 62%

PUGS: Perceptual Uncertainty for Grasp Selection in Underwater Environments

Onur Bagoren, Marc Micatka, Katherine A. Skinner, Aaron Marburg

机构 * University of Michigan（密歇根大学）； University of Washington（华盛顿大学）

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

Comments 8 pages, 4 figures Accepted to International Conference on Robotics and Automation (ICRA) 2024

2502.04615 2025-02-10 cs.CV cs.GR 62%

Neural Clustering for Prefractured Mesh Generation in Real-time Object Destruction

Seunghwan Kim, Sunha Park, Seungkyu Lee

机构 * Kyung Hee University（庆熙大学）

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

2501.18315 2025-01-31 cs.CV cs.RO 62%

Surface Defect Identification using Bayesian Filtering on a 3D Mesh

Matteo Dalle Vedove, Matteo Bonetto, Edoardo Lamon, Luigi Palopoli, Matteo Saveriano, Daniele Fontanelli

机构 * Università di Trento（特伦托大学）； Istituto Italiano di Tecnologia（意大利技术研究院）

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

Comments Presented at IMEKO2024 World Congress, Hamburg, Germany, 26-29 October 2024

1. 三维重建 4401 篇

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

TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization

CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation

Normal-guided Detail-Preserving Neural Implicit Function for High-Fidelity 3D Surface Reconstruction

HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation

SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modeling

ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping

GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priors

Neurally Integrated Finite Elements for Differentiable Elasticity on Evolving Domains

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

Mesh Compression with Quantized Neural Displacement Fields

DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow

Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video

3D Shape Tokenization via Latent Flow Matching

Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation

RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streaming

PseudoTouch: Efficiently Imaging the Surface Feel of Objects for Robotic Manipulation

PO-MSCKF: An Efficient Visual-Inertial Odometry by Reconstructing the Multi-State Constrained Kalman Filter with the Pose-only Theory

A Dataset and Benchmark for Shape Completion of Fruits for Agricultural Robotics

ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points

Perceptual Visual Quality Assessment: Principles, Methods, and Future Directions

PUGS: Perceptual Uncertainty for Grasp Selection in Underwater Environments

Neural Clustering for Prefractured Mesh Generation in Real-time Object Destruction

Surface Defect Identification using Bayesian Filtering on a 3D Mesh