3D 视觉 - arXivDaily 专题

2501.03830 2025-01-08 cs.CV cs.GR 62%

MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes

Germain Bregeon, Marius Preda, Radu Ispas, Titus Zaharia

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

2412.14974 2024-12-20 cs.CV cs.RO 62%

Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotations

Jianhua Sun, Yuxuan Li, Jiude Wei, Longfei Xu, Nange Wang, Yining Zhang, Cewu Lu

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

2412.14444 2024-12-20 cs.CV cs.AI cs.GR cs.LG 62%

GenHMR: Generative Human Mesh Recovery

Muhammad Usama Saleem, Ekkasit Pinyoanuntapong, Pu Wang, Hongfei Xue, Srijan Das, Chen Chen

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

2206.10274 2024-12-19 cs.RO cs.CV 62%

Attention-driven Next-best-view Planning for Efficient Reconstruction of Plants and Targeted Plant Parts

Akshay K. Burusa, Eldert J. van Henten, Gert Kootstra

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

Journal ref Biosystems Engineering, 246 (2024), 248-262

2412.11279 2024-12-17 cs.CV cs.AI cs.GR 62%

VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping

Hao Shao, Shulun Wang, Yang Zhou, Guanglu Song, Dailan He, Shuo Qin, Zhuofan Zong, Bingqi Ma, Yu Liu, Hongsheng Li

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

Comments project page: https://hao-shao.com/projects/vividface.html

2412.09620 2024-12-13 cs.CV cs.RO 62%

Learning Camera Movement Control from Real-World Drone Videos

Yunzhong Hou, Liang Zheng, Philip Torr

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

2412.06767 2024-12-10 cs.CV cs.GR 62%

MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views

Antoine Guédon, Tomoki Ichikawa, Kohei Yamashita, Ko Nishino

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

Comments Project Webpage: https://anttwo.github.io/matcha/

2412.00140 2024-12-03 cs.CV cs.GR 62%

Differentiable Topology Estimating from Curvatures for 3D Shapes

Yihao Luo

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

2411.14740 2024-11-25 cs.CV cs.AI cs.GR 62%

TEXGen: a Generative Diffusion Model for Mesh Textures

Xin Yu, Ze Yuan, Yuan-Chen Guo, Ying-Tian Liu, JianHui Liu, Yangguang Li, Yan-Pei Cao, Ding Liang, Xiaojuan Qi

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

Comments Accepted to SIGGRAPH Asia Journal Article (TOG 2024)

Journal ref ACM Transactions on Graphics (TOG) 2024, Volume 43, Issue 6, Article No.: 213, Pages 1-14

2411.12338 2024-11-20 cs.RO cs.CV 62%

Target Height Estimation Using a Single Acoustic Camera for Compensation in 2D Seabed Mosaicking

Xiaoteng Zhou, Yusheng Wang, Katsunori Mizuno

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

Comments 8 pages,conference

2411.07025 2024-11-12 cs.GR cs.CV 62%

Scaling Mesh Generation via Compressive Tokenization

Haohan Weng, Zibo Zhao, Biwen Lei, Xianghui Yang, Jian Liu, Zeqiang Lai, Zhuo Chen, Yuhong Liu, Jie Jiang, Chunchao Guo, Tong Zhang, Shenghua Gao, C. L. Philip Chen

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

Comments Homepage: https://whaohan.github.io/bpt , Code: https://github.com/whaohan/bpt

2410.21758 2024-10-30 cs.CV cs.RO 62%

DOFS: A Real-world 3D Deformable Object Dataset with Full Spatial Information for Dynamics Model Learning

Zhen Zhang, Xiangyu Chu, Yunxi Tang, K. W. Samuel Au

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

Comments 5 pages, 6 figures, 2024 CoRL Workshop on Learning Robot Fine and Dexterous Manipulation: Perception and Control

2410.20030 2024-10-29 cs.CV cs.AI cs.GR 62%

SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

Xuanchi Ren, Yifan Lu, Hanxue Liang, Zhangjie Wu, Huan Ling, Mike Chen, Sanja Fidler, Francis Williams, Jiahui Huang

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

Comments NeurIPS 2024. Project page: https://research.nvidia.com/labs/toronto-ai/scube/

2410.18630 2024-10-25 cs.CV cs.RO 62%

A Cranial-Feature-Based Registration Scheme for Robotic Micromanipulation Using a Microscopic Stereo Camera System

Xiaofeng Lin, Saúl Alexis Heredia Pérez, Kanako Harada

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

Comments Accepted by Advanced Robotics, Vol. 38, Issue 21

2403.16146 2024-10-23 cs.RO cs.CV 62%

Realtime Robust Shape Estimation of Deformable Linear Object

Jiaming Zhang, Zhaomeng Zhang, Yihao Liu, Yaqian Chen, Amir Kheradmand, Mehran Armand

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

Comments This paper has been accepted to IEEE ICRA 2024 as a contributed paper

Journal ref 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 2024, pp. 10734-10740

2410.08092 2024-10-11 cs.CV cs.RO 62%

UW-SDF: Exploiting Hybrid Geometric Priors for Neural SDF Reconstruction from Underwater Multi-view Monocular Images

Zeyu Chen, Jingyi Tang, Gu Wang, Shengquan Li, Xinghui Li, Xiangyang Ji, Xiu Li

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

Comments 8 pages, 9 figures, presented at IROS 2024

2410.06231 2024-10-11 cs.CV cs.GR cs.LG 62%

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Tianyuan Zhang, Zhengfei Kuang, Haian Jin, Zexiang Xu, Sai Bi, Hao Tan, He Zhang, Yiwei Hu, Milos Hasan, William T. Freeman, Kai Zhang, Fujun Luan

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

Comments webpage: https://relit-lrm.github.io/

2409.14778 2024-09-24 cs.CV cs.GR 62%

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

Egor Zakharov, Vanessa Sklyarova, Michael Black, Giljoo Nam, Justus Thies, Otmar Hilliges

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

2409.13418 2024-09-23 cs.CV cs.GR cs.LG 62%

Occupancy-Based Dual Contouring

Jisung Hwang, Minhyuk Sung

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

Comments Accepted to SIGGRAPH Asia (conference) 2024. Code: https://github.com/KAIST-Visual-AI-Group/ODC

2409.13151 2024-09-23 cs.CV cs.RO 62%

Learning Visual Information Utility with PIXER

Yash Turkar, Timothy Chase, Christo Aluckal, Karthik Dantu

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

2409.12379 2024-09-20 cs.CV cs.IT cs.RO math.IT 62%

Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach

Nastaran Darabi, Dinithi Jayasuriya, Devashri Naik, Theja Tulabandhula, Amit Ranjan Trivedi

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

2401.11067 2024-09-11 cs.CV cs.GR 62%

Make-A-Shape: a Ten-Million-scale 3D Shape Model

Ka-Hei Hui, Aditya Sanghi, Arianna Rampini, Kamal Rahimi Malekshan, Zhengzhe Liu, Hooman Shayani, Chi-Wing Fu

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

2409.05151 2024-09-10 cs.CV cs.GR 62%

Ultron: Enabling Temporal Geometry Compression of 3D Mesh Sequences using Temporal Correspondence and Mesh Deformation

Haichao Zhu

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

2409.00829 2024-09-04 cs.CV cs.CG cs.GR 62%

Curvy: A Parametric Cross-section based Surface Reconstruction

Aradhya N. Mathur, Apoorv Khattar, Ojaswa Sharma

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

2408.15114 2024-08-28 cs.CV cs.AI cs.GR cs.LG 62%

Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries

Amine Ouasfi, Adnane Boukhayma

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

Comments ICML 2024

2408.10198 2024-08-20 cs.CV cs.GR 62%

MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model

Minghua Liu, Chong Zeng, Xinyue Wei, Ruoxi Shi, Linghao Chen, Chao Xu, Mengqi Zhang, Zhaoning Wang, Xiaoshuai Zhang, Isabella Liu, Hongzhi Wu, Hao Su

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

Comments 20 pages, 9 figures

2408.06878 2024-08-14 cs.CV cs.GR 62%

PBIR-NIE: Glossy Object Capture under Non-Distant Lighting

Guangyan Cai, Fujun Luan, Miloš Hašan, Kai Zhang, Sai Bi, Zexiang Xu, Iliyan Georgiev, Shuang Zhao

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

2403.11796 2024-08-12 cs.CV cs.RO 62%

OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation

Haochen Jiang, Yueming Xu, Yihan Zeng, Hang Xu, Wei Zhang, Jianfeng Feng, Li Zhang

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

Comments This work is accepted by IROS 2024

2408.03178 2024-08-07 cs.CV cs.GR cs.LG 62%

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

Xingguang Yan, Han-Hung Lee, Ziyu Wan, Angel X. Chang

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

Comments Project Page: https://omages.github.io/

2311.16482 2024-07-30 cs.CV cs.GR 62%

Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars

Yang Liu, Xiang Huang, Minghan Qin, Qinwei Lin, Haoqian Wang

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

1. 三维重建 4390 篇

MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes

Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotations

GenHMR: Generative Human Mesh Recovery

Attention-driven Next-best-view Planning for Efficient Reconstruction of Plants and Targeted Plant Parts

VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping

Learning Camera Movement Control from Real-World Drone Videos

MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views

Differentiable Topology Estimating from Curvatures for 3D Shapes

TEXGen: a Generative Diffusion Model for Mesh Textures

Target Height Estimation Using a Single Acoustic Camera for Compensation in 2D Seabed Mosaicking

Scaling Mesh Generation via Compressive Tokenization

DOFS: A Real-world 3D Deformable Object Dataset with Full Spatial Information for Dynamics Model Learning

SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

A Cranial-Feature-Based Registration Scheme for Robotic Micromanipulation Using a Microscopic Stereo Camera System

Realtime Robust Shape Estimation of Deformable Linear Object

UW-SDF: Exploiting Hybrid Geometric Priors for Neural SDF Reconstruction from Underwater Multi-view Monocular Images

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

Occupancy-Based Dual Contouring

Learning Visual Information Utility with PIXER

Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach

Make-A-Shape: a Ten-Million-scale 3D Shape Model

Ultron: Enabling Temporal Geometry Compression of 3D Mesh Sequences using Temporal Correspondence and Mesh Deformation

Curvy: A Parametric Cross-section based Surface Reconstruction

Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries

MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model

PBIR-NIE: Glossy Object Capture under Non-Distant Lighting

OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars