Overview

3D reconstruction studies how to infer the shape and appearance of objects or scenes, along with camera positions and motion, from partial observations. Methods range from structure-from-motion and multi-view stereo to neural radiance fields, Gaussian splatting, signed distance fields, meshes, and feed-forward models that predict geometry directly; some also use diffusion priors, active view selection, or physical sensor models. Applications include mapping and robotics, digital twins, medical imaging, and human or object modeling, with evaluations often comparing both rendered views and geometric accuracy on indoor, outdoor, and specialized datasets. A central challenge is that realistic novel-view images do not always imply accurate, metrically consistent geometry, especially with sparse or unposed views, changing scenes, difficult materials, or limited computation.

Latest papers

CardsList

1,033 papers76 papers in the last four weeks, down 37% on the four weeks before. 0.6% of all new papers.

  1. SGAR: Feed-Forward 3D Reconstruction via Sparse Geometry-Guided Attention

    Nov 19, 2026Aoxiang Fan, Maria Pilligua, Corentin Dumery +23D ReconstructionFeed-Forward 3D Reconstruction

  2. FirstCross: Convex Single-Photon 3D Reconstruction from Sparse Views

    Nov 19, 2026Chi-Wei Lee, Cheng-Han Chiang, Yi-Chun Chang +23D ReconstructionSparse-View 3D Reconstruction

  3. AGE-Capture: Autonomous, General, and Efficient UAV Capture for High-Fidelity Scene Reconstruction

    Nov 19, 2026Xiaofeng Jin, Ningbo Bu, Matteo Frosi +3Aerial 3D Reconstruction3D Reconstruction

  4. SceneAnything: Agentic Reconstruction of Large-Scale Mesh Scenes from a Single Video

    Nov 19, 2026Bowen Xue, Saeed Hadadan, Fabrice Rousselle +33D Reconstruction3D Mesh Reconstruction

  5. Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction

    Nov 18, 2026Amani Kiruga, Mark Hamilton, Joshua B. Tenenbaum +43D ReconstructionMonocular 3D Reconstruction

  6. Beyond Appearance: Evidence-Guided Programmatic 3D Scene Reconstruction with Agentic Lighting Reasoning

    Nov 18, 2026Zeting Luo, Yifan Li, Shuai Yang3D Reconstruction

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

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

  8. TapTacTouch: Shape Completion from Sparse Tactile Contacts with Geometric Priors

    Nov 18, 2026Yoobin Shin, Jaeyoung Lee, Jieun Kang +33D Reconstruction3D Shape Completion

  9. Freeforward4d: Annotation-free feed-forward 4d reconstruction of driving scenes

    Nov 18, 2026Luosong Guo, Xiang Yang, Chaoyang Li +64D Reconstruction3D Reconstruction

  10. GaussLearner: 3D Gaussian Primitives as Self-Regulating Continual Learners

    Nov 18, 2026Gaoxiang Linghu, Haonan Zhou, Xuanhe Liu +43D Gaussian Splatting3D Reconstruction

  11. 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

  12. Trust the Ray, Not the Depth: Ray-Lateral Agreement for Multi-View 3D Human Pose Fusion

    Nov 17, 2026Farnoosh Koleini, Ahmed Helmy, Pu Wang +13D Human Pose Estimation3D Reconstruction

  13. Any2Building: Unifying Point Clouds and Images for Building Reconstruction via Shared Spatial Queries

    Nov 17, 2026Hongye Hou, Zhuoxiao Li, Liu Xiangyu +63D ReconstructionUrban Scene Reconstruction

  14. Improving On-board Shape Models Using Sun Sensors and Implicit Representations

    Nov 17, 2026Zacharia A. Rudge, Giacomo Acciarini, Dario Izzo +33D ReconstructionDeformable Shape Reconstruction

  15. CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference

    Nov 17, 2026Oleg Pavlov, Nikita Gavrilov, Soslan Kabisov +43D ReconstructionParametric CAD Modeling

  16. MAVE: Reconstructing Editable 3D Blockouts from Film Shots

    Nov 17, 2026Yifan Chang, Jian Yang, Jiangnan Shao +63D ReconstructionDynamic Scene Reconstruction

  17. Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery

    Nov 16, 2026Yunchan Jeon, SooGon Kim, Seungwook Kim +23D ReconstructionSingle-View 3D Reconstruction

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

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

  19. ReScene: Incremental Scene Chronology from Sparse Revisits

    Nov 16, 2026Wei Qin Chuah, Zeji Hui, Amirali Khodadadian Gostar +13D ReconstructionDynamic Scene Reconstruction

  20. SemLite-GS: Semantic-Selective Parallel Gaussian Splatting for Lightweight Building Reconstruction from UAV Oblique Imagery

    Nov 15, 2026Tengfei Wang, Xin Wang, Zihan Li +43D ReconstructionAerial 3D Reconstruction

  21. TetraCoder: Adaptive Tetrahedral Encoding for Neural Fields

    Nov 13, 2026Daniele Della Pietra, Antonella Rech, Nicola Conci +1Neural Representation GeometryNeural Rendering

  22. 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

  23. TelePhysica: Agentic Reconstruction of Physically Interactive Scenes

    Nov 13, 2026Ruiqi Shu, Xufeng Zhan, Yuanzhi Liang +3Physical Consistency in Video GenerationPhysics-Aware 3D Scene Reconstruction

  24. BrickFlow: Connectivity-Guided Brick Reconstruction

    Nov 12, 2026Peter Kulits, Cordelia Schmid3D ReconstructionSingle-View 3D Reconstruction

  25. Kosmo-GFM: A Production-Ready Geometry Foundation Model

    Nov 12, 2026Sheng Tang, Shengzhe Wei, Tiancheng Chen +293D ReconstructionMulti-View Geometry

  26. HybridCT: ML Accelerated Tomography for Climate Relevant 3D Cloud Observations

    Nov 12, 2026Linda Forster, Nicholas J. LaHaye, Marcin J. Kurowski +33D ReconstructionImage Reconstruction