Multi-View 3D Reconstruction

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

308 papers30 papers in the last four weeks, down 17% on the four weeks before. 0.2% of all new papers.

  1. RAPID: Reconstruction Accelerated by Polarization-Informed Depth for 2D Gaussian Splatting

    Nov 18, 2026Daisong Ouyang, Linlin Xia, Liangkun Yan +43D Reconstruction3DGS Acceleration

  2. Layer-Matched Sparse Attention for Low-Redundancy 3D Reconstruction

    Nov 17, 2026Sammam Mahdi, Fariha Binta Salim, K. M. Jubair Sami +13D ReconstructionMulti-View 3D Reconstruction

  3. π4π^4: A Foundation Model for 4D Scene Geometry and Motion

    Nov 17, 2026Yifan Wang, Weiguang Zhao, Ni Yang +44D Scene UnderstandingMulti-View 3D Reconstruction

  4. ARG-Avatar: Animation-Rendering Guidance for Efficient Feedforward Avatar Reconstruction

    Nov 17, 2026Jianjin Xu, Soham Dasgupta, Fernando De la Torre3D Human Reconstruction3D Avatar Generation

  5. Déjà-Events: Multi-view 3D Geometry with Event Cameras via Sparsity-Aware Adaptive Gating

    Nov 16, 2026Arda Cinar Demirtas, Pablo Varela Bernal, Marc Pollefeys +1Multi-View Depth EstimationEvent-Based Vision

  6. Efficient Multi-View Generation with Iterative Global-Local Proxy Attention

    Nov 16, 2026Wei Tan, Kunming Luo, Hongyu Yan +4Multi-View Image SynthesisMulti-View Diffusion Models

  7. Pointillist Maize: 3D Reconstruction of Field-Grown Maize Using RGB UAV Imagery

    Nov 16, 2026Dewi Endah Kharismawati, Toni Kazic3D ReconstructionAerial 3D Reconstruction

  8. Deep Bundle Adjustment

    Nov 13, 2026Pak Hong Chui, Hector Andrade-Loarca, Daniel CremersMulti-View 3D ReconstructionStructure from Motion

  9. Eco3R: Pinned-Key Inference for Efficient and Streamable Feed-Forward 3D Reconstruction from Long Videos

    Nov 13, 2026Hongsen Cao, Shanxin Yuan, Mona Jaber +13D ReconstructionMulti-View 3D Reconstruction

  10. X-Strata: Separating Aneurysms and Overlapping Vessels into Layers from 2D X-ray Angiography

    Nov 13, 2026Zhihong Wen, Congzhou Chen, Hucheng Li +9Medical Image AnalysisMedical Imaging

  11. Training-Free Acceleration of Multi-View 3D Transformers via Regime-Aware Attention Approximation

    Nov 13, 2026Muhammed Izzet Sezer, Sevval Belkis Dikkaya3D ViTsEfficient ViTs

  12. DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction

    Nov 10, 2026Xiao Ren, Yu Liu, Ning An +43D Gaussian SplattingMulti-View 3D Reconstruction

  13. Budget-aware Correspondence-driven View Selection for Real-time 3D Perception of Mobile Robots

    Nov 9, 2026Vaishnav Ramesh, Jacob Carter, Shivali J. Patel +23D ReconstructionMulti-View 3D Reconstruction

  14. Martine: Benchmarking Multi-View 3D Surface Reconstruction Across Viewpoint Coverage, Resolution, and Lighting

    Nov 8, 2026Robin Bruneau, Baptiste Brument, Frederic Giraud +53D Reconstruction Benchmarks3D Reconstruction

  15. AI-Driven Repair of Missing Automotive Components

    Nov 6, 2026Kazim Abbas, Zheng Liu3D Shape Completion3D Reconstruction

  16. Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images

    Nov 5, 2026David G. Shatwell, Mubarak Shah3D ReconstructionMulti-View 3D Reconstruction

  17. Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments

    Nov 3, 2026Zhipeng Zhong, Matthew Coombes, Cunjia Liu3D Reconstruction3D Reconstruction Benchmarks

  18. Phase-DGS: Phase-guided Dynamic Gaussian Splatting from Unsynchronized Multi-view Video

    Nov 3, 2026Hosung Jeon, Jun Young Jeong, Sangwoon Kwak +5Dynamic Scene ReconstructionDynamic Gaussian Splatting

  19. Solv3R: 3D Looped Transformer as a Multi-view Solver

    Nov 2, 2026Jeong-gi Kwak, Andrea Tagliasacchi, Sho Kagami +23D ReconstructionMulti-View 3D Reconstruction

  20. OctreeSplat: Hierarchical Octree-Guided Feed-Forward Gaussian Splatting

    Nov 2, 2026Yibin Zhao, Yihan Pan, Wenli Yang +23D Gaussian SplattingNovel View Synthesis

  21. Reconstruction as Spatial Evaluation: Diagnosing Cross-View Spatial Intelligence in Large Vision-Language Models

    Nov 1, 2026Junfei Wu, Qiuyue Wang, Xuhong Huang +8Spatial Reasoning BenchmarksMultimodal Spatial Reasoning

  22. Rethinking Asymmetry in Self-Supervised 3D Geometry Learning

    Oct 30, 2026Gyeongjin Kang, Freeman Cheng, Botao Ye +33D Representation LearningMulti-View 3D Reconstruction

  23. ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting

    Oct 29, 2026Houqiang Zhong, Tianchi Zhu, Qiang Hu +33D Gaussian Splatting3DGS Training

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

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

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

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