Multi-View 3D Reconstruction

Ask about this topic

Overview

Multi-view 3D reconstruction combines images or video from different viewpoints to estimate camera poses, depth, surfaces, and sometimes appearance or motion. Classical structure-from-motion and multi-view stereo rely on feature matching, triangulation, and bundle adjustment, while neural methods use NeRFs, Gaussian splatting, and feed-forward geometry transformers to infer 3D from images. Current work also adds depth and vision-model priors, selects informative views, and handles difficult cases such as uncalibrated cameras, dynamic scenes, reflective materials, and wide-angle or satellite imagery. A central challenge is balancing accurate, complete geometry across sparse or inconsistent views with the speed, memory, and generalization needed for large-scale and real-time use.

Latest papers

CardsList

277 papers34 papers in the last four weeks, up 21% on the four weeks before. 0.2% of all new papers.

  1. GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

    Oct 27, 2026Jiale Wang, Chen Zhao, Haoyang Zhang +63D Gaussian SplattingNovel View Synthesis

    Xi’an Jiaotong University · Horizon Robotics · EPFL +1

  2. Any3R: Feedforward 3D Reconstruction from Any Camera Type

    Oct 26, 2026Jingong Chen, Qingwen Zhang, Youming Deng +53D ReconstructionMulti-View 3D Reconstruction

    South Dakota State University · Aalto University · KTH Royal Institute of Technology +3

  3. Does VGGT Know What It Does Not Know?

    Oct 26, 2026Adityan Thirumani Srinivasan, David NordströmUQ for 3D ReconstructionFeed-Forward 3D Reconstruction

    University of Wisconsin–Madison · Chalmers University of Technology

  4. Generative Structure from Motion with Native 3D Diffusion

    Oct 26, 2026Haobin Duan, Binbin Huang, Mochu Xiang +4Structure from MotionMulti-View 3D Reconstruction

    The University of Hong Kong · Transengram · Tencent

  5. CVTSplat: Multi-view Reconstruction Using an Adaptive Centroidal Voronoi Tessellation

    Oct 26, 2026Briac Toussaint, Diego Thomas, Jean-Sébastien Franco +2Multi-View 3D Reconstruction

    Max Planck Institute for Informatics, Saarbrücken, Germany · Kyushu University, Fukuoka, Japan · Inria, Grenoble, France

  6. Birth-Death Structural Learning for 3D Gaussian Splatting

    Oct 25, 2026Quan Tran Hong, Long Nguyen-Chi, Binh T. Nguyen3D Gaussian SplattingAdaptive Gaussian Densification

    Center for AI Research, VinUniversity, Hanoi, Vietnam

  7. FreeView: Robust 3D Reconstruction from Uncurated Views

    Oct 24, 2026Junho Kim, Hyunyoung Choi, Seongwon Lee3D ReconstructionMulti-View 3D Reconstruction

    School of Electrical Engineering, Kookmin University, Seoul 02707, South Korea

  8. CompMVR: Compression-Aware Multi-View Restoration Using Diffusion Models for Geometrically Consistent 3D Reconstruction

    Oct 23, 2026Dong-hwi Kim, Chaewon Moon, Hojun Song +13Multi-View ConsistencyMulti-View 3D Reconstruction

    Kyungpook National University, Republic of Korea · Adobe Research, USA

  9. BlazeVGGT: 13x Faster VGGT at 2,000 Frames via Camera Token without Training

    Oct 21, 2026Shujun Yao, Junhui Lin, Congying Han +3Multi-View 3D ReconstructionFeed-Forward 3D Reconstruction

    University of Chinese Academy of Sciences, Beijing, China · the University of Maryland, College Park, MD, USA · Beijing University of Posts and Telecommunications, Beijing, China

  10. PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos

    Oct 21, 2026Shangjia Liu, Jinxi Li, Siyuan Zhou +2Dynamic Scene ReconstructionMotion Representation Learning

    Spatial Intelligence Group, The Hong Kong Polytechnic University, Hong Kong SAR, China · vLAR Group, The Hong Kong Polytechnic University, Hong Kong SAR, China

  11. ReDT: Resolution-Decoupled Visual Geometry Transformer

    Oct 18, 2026Abteen Arab, Guile Wu, Dongfeng Bai3D ViTs3D Reconstruction

    Huawei Noah’s Ark Lab · University of British Columbia

  12. Motion- and Gravity-Aware Feedforward 3D Reconstruction

    Oct 15, 2026Shiyao Qian, Yuan Ren, Dongfeng BaiMulti-View 3D ReconstructionFeed-Forward 3D Reconstruction

    Huawei Noah’s Ark Lab, Markham, ON, Canada. · University of Toronto, Toronto, ON, Canada.

  13. Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation

    Oct 15, 2026Sheng Ye, Jiangke Lin, Fudong Wang +33D Gaussian SplattingMulti-View 3D Reconstruction

    Tsinghua University · Ant Group, Inclusion AI

  14. GRASE: Geometry-native Real-to-sim Agentic Scene Modeling from Video

    Oct 15, 2026Zhaorui Lin, Haohan Liu, Zhen Chen +1Real-to-Sim Transfer3D Scene Representation

    Xi’an Jiaotong University (xjtu.edu.cn) · Fuzhou University (fzu.edu.cn) · Adobe Systems (adobe.com) +1

  15. WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World

    Oct 13, 2026Mengchen Zhang, Yang Li, Chunshi Wang +23D Reconstruction3D Mesh Reconstruction

    Zhejiang University · Tencent Hunyuan · Fudan University

  16. CoTL: Compact Token Learning for 3D Scene Representation

    Oct 13, 2026Han Liang, Sibo Wu, Anpei Chen +13D Scene RepresentationMulti-View 3D Reconstruction

    TU Munich · MCML · Westlake University

  17. UniMetric: Universal Metric Scale Recovery for Visual Geometry Foundation Models

    Oct 12, 2026Lei Yang, Yuner Zhang, Ziyang Liu +53D Reconstruction3D Foundation Models

    Nanyang Technological University · Carnegie Mellon University · The Hong Kong Polytechnic University +3

  18. WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention

    Oct 12, 2026Mijeong Kim, Kyujin Lim, Bohyung HanRotary Positional EmbeddingsMulti-View 3D Reconstruction

    ECE, Seoul National University · IPAI, Seoul National University

  19. Graph3R: Unifying View Graph Initialization with Feed-Forward Reconstruction

    Oct 12, 2026Jingwen Yu, Hengli Wang, Jianhao Jiao +33D ReconstructionMulti-View 3D Reconstruction

    Hong Kong University of Science and Technology · Southern University of Science and Technology · China Merchants Group, LionRock AI Lab +1

  20. Sharper Frames, Worse Rooms: Viewpoint Coverage Dominates Image Quality in Feed-Forward 3D Reconstruction

    Oct 11, 2026Alibek Dadajonov, Hikmatillo UmarhojiyevFeed-Forward 3D ReconstructionMulti-View 3D Reconstruction

    Arbuz AI

  21. Volume Rendering with Metric--Phase Fields for Thin Structures and Sign-Ambiguous Geometry

    Oct 9, 2026Junkai Deng, Jiayi Kong, Xuhui Chen +53D ReconstructionMulti-View 3D Reconstruction

    College of Computing and Data Science, Nanyang Technological University, Singapore · Key Laboratory of System Software (Chinese Academy of Sciences), Institute of Software, Chinese Academy of Sciences, and the University of Chinese Academy of Sciences · Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China +1

  22. Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction

    Oct 8, 2026Utkarsh Saxena, Ruijing Yang, Mehdi Rezagholizadeh +33D Foundation ModelsFeed-Forward 3D Reconstruction

    Advanced Micro Devices Inc. (AMD)

  23. Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion

    Oct 8, 2026Kartik Bali, Mahish Guru, Yiderigun Borjigin +3Active View Selection3D Reconstruction

    Helmholtz-Zentrum Hereon · Leuphana Universität Lüneburg · Universität des Saarlandes +1

  24. Less Context, Better Geometry: Masked Geometric Encoder for Robust 3D Foundation Models

    Oct 5, 2026Zhimin Shao, Xijun Liu, Zhaoliang Zhang +43D Foundation ModelsToken Merging

    Department of Electrical and Computer Engineering Johns Hopkins University · Department of Data Science University of Virginia

  25. VGGT-Bridge: Beyond Sequential Pose Graphs via Coarse-Stride Skip Edges

    Oct 5, 2026Sungjae Choi, Hanna Bae, Sunghyun Baek +13D ViTsStreaming 3D Reconstruction

    Korea Advanced Institute of Science and Technology, South Korea

  26. MaRO-GS: Mask-Robust Object-Centric Gaussian Splatting from Inconsistent Multi-view Masks

    Oct 5, 2026Eunji Kim, Gahyeon Kim, Gianella Cravioto +4Object-Centric 3D Reconstruction3D Gaussian Splatting

    School of Computer Science and Engineering Kyungpook National University, Daegu, Republic of Korea

  27. LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning

    Oct 3, 2026Sinan Wang, Jinjin He, Yuchen Sun +33D Gaussian SplattingMulti-View 3D Reconstruction

    Georgia Institute of Technology

  28. T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images

    Oct 2, 2026Atsuhiro Noguchi, Tianhan Xu, Yiming Liang +5Large-Scale 3D Reconstruction3D Reconstruction

    Preferred Networks, Inc. · The University of Tokyo

  29. PocketSplat: Mobile Gaussian Reconstruction via World-Space Latent Allocatio

    Oct 2, 2026Wenzhi Guo, Xianda Chen, Dongxuan Chen +23D Gaussian Splatting3D Reconstruction

  30. EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation

    Oct 1, 2026Tongyu Wu, Jacob Edwards, Ziteng Cui +23D Gaussian SplattingIntrinsic Image Decomposition

    Xi’an Jiaotong University · University of East Anglia · University of Tokyo