3D 视觉

Sparse-View 3D Reconstruction: Recent Advances and Open Challenges

Tanveer Younis, Zhanglin Cheng

机构 * Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院） ； Shenzhen VisuCA Key Lab, Shenzhen, China（深圳VisuCA实验室，中国） 纠错

专题命中 三维重建 ：3D reconstruction(title,abstract)；NeRF(abstract)；Gaussian Splatting(abstract)；分类 cs.CV

Comments 30 pages, 6 figures

IXGS-Intraoperative 3D Reconstruction from Sparse, Arbitrarily Posed Real X-rays

Sascha Jecklin, Aidana Massalimova, Ruyi Zha, Lilian Calvet, Christoph J. Laux, Mazda Farshad, Philipp Fürnstahl

机构 * Research in Orthopedic Computer Science, Balgrist University Hospital, Zurich, 8008, Switzerland（骨科计算机科学研究所，巴尔格里斯大学医院，苏黎世，8008，瑞士） ； The Australian National University, Canberra, ACT 2601, Australia（澳大利亚国立大学，堪培拉，ACT 2601，澳大利亚） ； Department of Orthopedics, Balgrist University Hospital, University of Zurich, Zurich, 8008, Switzerland（骨科系，巴尔格里斯大学医院，苏黎世大学，苏黎世，8008，瑞士） 纠错

专题命中 三维重建 ：3D reconstruction(title,abstract)；Gaussian Splatting(abstract)；novel view synthesis(abstract)；分类 cs.CV

Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction

Wenyu Li, Sidun Liu, Peng Qiao, Yong Dou

机构 * National University of Defence Technology（国防科技大学） 纠错

专题命中 三维重建 ：3D reconstruction(title,abstract)；3D vision(abstract)；point cloud(abstract)；分类 cs.CV

MicroDreamer: Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction

Luxi Chen, Zhengyi Wang, Zihan Zhou, Tingting Gao, Hang Su, Jun Zhu, Chongxuan Li

专题命中 三维重建 ：3D generation(title,abstract)；Gaussian Splatting(abstract)；3D reconstruction(abstract)；分类 cs.CV

Automatic Robot Hand-Eye Calibration Enabled by Learning-Based 3D Vision

Leihui Li, Xingyu Yang, Riwei Wang, Xuping Zhang

专题命中 三维重建 ：3D vision(title,abstract)；3D reconstruction(abstract)；point cloud(abstract)；分类 cs.RO

Comments Accepted by Journal of Intelligent & Robotic Systems

A Pixel Is Worth More Than One 3D Gaussians in Single-View 3D Reconstruction

Jianghao Shen, Nan Xue, Tianfu Wu

专题命中 三维重建 ：3D reconstruction(title)；Gaussian Splatting(abstract)；3DGS(abstract)；novel view synthesis(abstract)

Comments preprint, under review

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

David Charatan, Sizhe Li, Andrea Tagliasacchi, Vincent Sitzmann

专题命中 三维重建 ：3D reconstruction(title,abstract)；Gaussian Splatting(abstract)；novel view synthesis(abstract)；分类 cs.CV

Comments Project page: https://dcharatan.github.io/pixelsplat

UNeR3D: Versatile and Scalable 3D RGB Point Cloud Generation from 2D Images in Unsupervised Reconstruction

Hongbin Lin, Juangui Xu, Qingfeng Xu, Zhengyu Hu, Handing Xu, Yunzhi Chen, Yongjun Hu, Zhenguo Nie

专题命中 三维重建 ：point cloud(title,abstract)；3D vision(abstract)；3D reconstruction(abstract)；分类 cs.CV

Comments 17 pages

ReconFusion: 3D Reconstruction with Diffusion Priors

Rundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park, Ruiqi Gao, Daniel Watson, Pratul P. Srinivasan, Dor Verbin, Jonathan T. Barron, Ben Poole, Aleksander Holynski

专题命中 三维重建 ：3D reconstruction(title,abstract)；NeRF(abstract)；novel view synthesis(abstract)；分类 cs.CV

Comments Project page: https://reconfusion.github.io/

RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians

Shenxing Wei, Jinxi Li, Yafei Yang, Siyuan Zhou, Bo Yang

机构 * vLAR Group, The Hong Kong Polytechnic University（vLAR组，香港理工大学） 纠错

专题命中 三维重建 ：point cloud(title,abstract)；3DGS(abstract)；分类 cs.CV、cs.GR、cs.RO

Comments ICCV 2025 Highlight. Shenxing and Jinxi are co-first authors. Code and data are available at: https://github.com/vLAR-group/RayletDF

Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond

Holo360D: 一个大规模真实世界数据集，具有连续轨迹，用于推进全景3D重建及更广泛领域

Jing Ou, Zidong Cao, Yinrui Ren, Zhuoxiao Li, Jinjing Zhu, Tongyan Hua, Shuai Zhang, Hui Xiong, Wufan Zhao

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； South China Normal University（华南师范大学） 纠错

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

AI总结 本文提出Holo360D数据集，包含109495张全景图像及注册点云、网格和对齐相机姿态，通过连续轨迹和高完整性深度图提升全景3D重建性能，建立新基准并提供有效微调策略。

Comments Datasets Link: https://github.com/Jou719/Holo360D

Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction

Hestia：面向高效3D重建的体素-面感知分层最佳视角获取

Cheng-You Lu, Zhuoli Zhuang, Nguyen Thanh Trung Le, Da Xiao, Yu-Cheng Chang, Thomas Do, Srinath Sridhar, Chin-teng Lin

机构 * University of Technology Sydney（悉尼技术大学） ； Brown University（布朗大学） 纠错

专题命中 三维重建 ：3D reconstruction(title,abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.RO

AI总结 本文提出Hestia，一种面向高效3D重建的体素-面感知分层最佳视角获取方法，通过改进的规划器组件提升鲁棒性和性能，实验显示在覆盖比和Chamfer距离上均有显著提升。

Comments Accepted to the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026

ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models

ArtiFixer：利用自回归扩散模型增强和扩展3D重建

Riccardo de Lutio, Tobias Fischer, Yen-Yu Chang, Yuxuan Zhang, Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Katarina Tothova, Zan Gojcic, Haithem Turki

机构 * NVIDIA ； NVIDIA Santa Clara USA（NVIDIA） ； NVIDIA Zurich Switzerland（NVIDIA） ； Cornell University（康奈尔大学） ； University of Toronto（多伦多大学） ； Vector Institute（向量研究所） 纠错

专题命中 三维重建 ：3D reconstruction(title)；Gaussian Splatting(abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.GR

AI总结 ArtiFixer通过自回归扩散模型提升3D重建质量，解决现有方法在未观测区域的外推问题。

Comments Video results: https://artifixer2026.github.io/

High-fidelity 3D reconstruction for planetary exploration

高保真行星探测的3D重建

Alfonso Martínez-Petersen, Levin Gerdes, David Rodríguez-Martínez, C. J. Pérez-del-Pulgar

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

AI总结 本文提出了一种结合NeRF和高斯点绘的自动化3D重建管道，用于在极端环境下实现高保真的行星探测

Comments 7 pages, 3 figures, conference paper

Journal ref IEEE Conference on Artificial Intelligence (CAI) 2026, Special Session on AI for Space Exploration

S-MUSt3R: Sliding Multi-view 3D Reconstruction

S-MUSt3R：滑动多视角三维重建

Leonid Antsfeld, Boris Chidlovskii, Yohann Cabon, Vincent Leroy, Jerome Revaud

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

AI总结 S-MUSt3R通过序列分割和轻量级优化实现高效单目三维重建，利用MUSt3R模型在大规模RGB流中实现高精度重建。

Comments 8 pages, 5 figures, 5 tables

Under-Canopy Terrain Reconstruction in Dense Forests Using RGB Imaging and Neural 3D Reconstruction

利用RGB成像和神经3D重建进行密林下的地形重建

Refael Sheffer, Chen Pinchover, Haim Zisman, Dror Ozeri, Roee Litman

机构 * Rafael Advanced Defense Systems inc., Israel（拉斐尔先进防御系统公司，以色列） ； Bar-Ilan University, Israel（巴伊兰大学，以色列） 纠错

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

AI总结 利用RGB图像和神经3D重建技术，实现密林下的地形重建，提供一种低成本、高精度的替代方案。

Comments WACV 2026 CV4EO

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

MapAnything: 通用前馈度量3D重建

Nikhil Keetha, Norman Müller, Johannes Schönberger, Lorenzo Porzi, Yuchen Zhang, Tobias Fischer, Arno Knapitsch, Duncan Zauss, Ethan Weber, Nelson Antunes, Jonathon Luiten, Manuel Lopez-Antequera, Samuel Rota Bulò, Christian Richardt, Deva Ramanan, Sebastian Scherer, Peter Kontschieder

机构 * Meta Reality Labs（Meta现实实验室） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

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

AI总结 Map Anything是一种统一的前馈模型，通过输入图像和几何信息，直接回归度量3D场景几何，适用于多种3D视觉任务。

Comments 3DV 2026. Project Page: https://map-anything.github.io/

A Survey on Event-driven 3D Reconstruction: Development under Different Categories

Chuanzhi Xu, Haoxian Zhou, Haodong Chen, Vera Chung, Qiang Qu

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

Comments We have decided not to submit this article and plan to withdraw it from public display. The content of this article will be presented in a more comprehensive form in another work

Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation

Junlin Han, Jianyuan Wang, Andrea Vedaldi, Philip Torr, Filippos Kokkinos

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

Comments ICML 25. Project page: https://junlinhan.github.io/projects/flex3d/

OmniIndoor3D: Comprehensive Indoor 3D Reconstruction

Xiaobao Wei, Xiaoan Zhang, Hao Wang, Qingpo Wuwu, Ming Lu, Wenzhao Zheng, Shanghang Zhang

机构 * Peking University（北京大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

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

Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction

Seungtae Nam, Xiangyu Sun, Gyeongjin Kang, Younggeun Lee, Seungjun Oh, Eunbyung Park

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

Comments Project page: https://stnamjef.github.io/GenerativeDensification/

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video

Xiaohao Xu, Tianyi Zhang, Shibo Zhao, Xiang Li, Sibo Wang, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Sebastian Scherer, Xiaonan Huang

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

Comments Accepted by ICLR 2025; 92 Pages; Project Repo: https://github.com/Xiaohao-Xu/SLAM-under-Perturbation. arXiv admin note: substantial text overlap with arXiv:2406.16850

Robotic Arm Platform for Multi-View Image Acquisition and 3D Reconstruction in Minimally Invasive Surgery

Alexander Saikia, Chiara Di Vece, Sierra Bonilla, Chloe He, Morenike Magbagbeola, Laurent Mennillo, Tobias Czempiel, Sophia Bano, Danail Stoyanov

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

Comments 8 pages, 5 figures, 3 tables. This work has been submitted to the IEEE for possible publication

3D Reconstruction with Fast Dipole Sums

Hanyu Chen, Bailey Miller, Ioannis Gkioulekas

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

Comments project page: https://imaging.cs.cmu.edu/fast_dipole_sums

A Review of 3D Reconstruction Techniques for Deformable Tissues in Robotic Surgery

Mengya Xu, Ziqi Guo, An Wang, Long Bai, Hongliang Ren

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

Comments To appear in MICCAI 2024 EARTH Workshop. Code availability: https://github.com/Epsilon404/surgicalnerf

Survey on Fundamental Deep Learning 3D Reconstruction Techniques

Yonge Bai, LikHang Wong, TszYin Twan

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

Fast Point Cloud to Mesh Reconstruction for Deformable Object Tracking

Elham Amin Mansour, Hehui Zheng, Robert K. Katzschmann

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

Comments 8 pages with appendix,16 figures

MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion

Xin-Yang Zheng, Hao Pan, Yu-Xiao Guo, Xin Tong, Yang Liu

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

SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction

Zhizhuo Zhou, Shubham Tulsiani

专题命中 三维重建 ：3D reconstruction(title,abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.GR

Comments project page: https://sparsefusion.github.io/ v2: typo corrected in table 3 v3: added ablation

Edge Preserving Implicit Surface Representation of Point Clouds

Xiaogang Wang, Yuhang Cheng, Liang Wang, Jiangbo Lu, Kai Xu, Guoqiang Xiao

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