Overview

3D human reconstruction aims to recover a person's body shape, pose, clothing, appearance, and motion from images, video, or other sensors, often alongside cameras and surrounding scenes. Methods range from fitting parametric models such as SMPL-X using keypoints and silhouettes to transformer-based mesh predictors and diffusion models that generate missing views or poses; neural fields and 3D Gaussian splatting support detailed, animatable appearance. Multi-view geometry, temporal motion priors, and contact or physics constraints help resolve ambiguity, with benchmarks including 3DPW and EMDB for motion and CAPE and THuman for clothed geometry and avatars. Feed-forward models are making reconstruction faster, but monocular scale ambiguity, occlusion, hands, loose garments, and consistency between people, scenes, and motion remain difficult, especially beyond controlled capture settings.

Latest papers

CardsList

111 papers7 papers in the last four weeks, down 56% on the four weeks before. 0.1% of all new papers.

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

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

  2. Toward Uncertainty-Aware, Physics-Grounded Human World Models

    Nov 2, 2026Yufei Zhang, Zijun CuiWorld ModelsHuman Motion Prediction

  3. Mesh-Agnostic Refinement Models for Latent Space Encoding of 3D Human Body Shapes

    Nov 2, 2026Chaima Zouaoui, Jonathan Cerqueira, Sylvain Arguillere +43D Human Reconstruction3D Mesh Deformation

  4. InfantNet: A Large Scale Dataset for Infant Body Pose and Shape Estimation

    Oct 29, 2026Zhipeng Hui, Jiahao Wang, Xun Dong +13Human Pose Estimation3D Human Pose Estimation

  5. Complexity-guided Regularization for Generalizable Human Gaussian Splatting

    Oct 26, 2026Gun Ryu, Gi-Mun Um, Won-Sik Cheong +13D Gaussian SplattingGaussian Splatting

  6. MedBOE: Optimization-Based Estimation of Complete Patient Body Models from Whole-Body Medical Imaging

    Oct 20, 2026Hoijoon Jung, Yuhao Wei, Mingxiao Tu +33D Medical ImagingDeformable Shape Reconstruction

  7. ExMR: Extremity Motion Refinement for Monocular Human Motion Capture

    Oct 19, 2026Tom Wehrbein, Bodo Rosenhahn3D Human Reconstruction3D Human Motion Reconstruction

  8. Dense4D: Pixel-Level 4D Human Correspondence

    Oct 15, 2026Rıza Alp Güler3D Point TrackingNon-Rigid Shape Correspondence

  9. OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching

    Oct 14, 2026Minghao Liu, Tutian Tang3D Human Reconstruction3D Human Pose Estimation

  10. A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics

    Oct 14, 2026Hao-Jen Chien, Wei-Lun Chao, Yu-Lun Liu3D Human Reconstruction3D Reconstruction

  11. EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ

    Oct 13, 2026Yunsong Zhou, Xuekun Jiang, Haiqi Shen +113D Human ReconstructionWearable Sensing

  12. TAP3D: Thermal-Assisted 3D Human Point Clouds

    Oct 8, 2026Xie Zhang, Chengxiao Li, Xuan Liu +13D Human ReconstructionPoint Cloud Generation

  13. R1A-PC: Physics-Guided Electromagnetic Inversion of Three-Dimensional Human Point Clouds in Complex Static Environments

    Oct 4, 2026Xudong Yuan, Ruyun Xu, Jingtai Yang +13D ReconstructionPoint Cloud Surface Reconstruction

  14. FlowHMR: Physically Plausible Motion Capture from Video

    Oct 2, 2026Zhanke Wang, Chengfeng Zhao, Qing Shuai +8Style-Conditioned Motion Generation3D Human Motion Reconstruction

  15. PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video

    Sep 30, 2026Rikhat Akizhanov, Yangsong Zhang, Nikolai Kaliazin +5Contact Force EstimationHuman Pose Estimation

  16. Geometry-Preserving Human-to-Robot Upper-Body Motion Retargeting from Monocular Video

    Sep 29, 2026Xiaoyu Yang, Sen Han, Da Li +1Motion Retargeting3D Human Reconstruction

  17. Privacy-Preserving Full-Body Meshing from mmWave Radar via Mesh Foundation Model Supervision

    Sep 28, 2026Shuxing Zhang, Yongquan Ni, Zhenyu Ding +1Millimeter-Wave RadarmmWave Radar Sensing

  18. Ego-Exo4D Human Meshes Dataset: 4D Human Motion Reconstruction for Ego-Exo Captures

    Sep 24, 2026Abhiram Maddukuri, Georgios Pavlakos4D ReconstructionHuman Mesh Recovery

  19. PHOSA: Photorealistic 3D Sign Avatar Modeling and Benchmark

    Sep 24, 2026Haodong Wang, Hezhen Hu, Wengang Zhou +13D Avatar Generation3D Human Reconstruction

  20. WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model

    Sep 24, 2026Jerrin Bright, John ZelekVision Foundation Model AdaptationDynamic Scene Reconstruction

  21. Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responses

    Sep 21, 2026Jiankuo Zhao, Xiangyu Zhu, Jijie Li +33D Gaussian Splatting3D Avatar Generation

  22. DirtyMoCap: Robust Motion Capture from Unconstrained Markers

    Sep 17, 2026Long Wang, Shuting Zhao, Shen Yan +5Gauss-Newton Optimization3D Human Pose Estimation

  23. Tele360: Real-Time Feed-Forward Human Reconstruction from Sparse Unposed Cameras

    Sep 14, 2026Hanzhang Tu, Zhanfeng Liao, Wei Min +23D Gaussian SplattingCamera Pose Estimation

  24. Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need

    Sep 10, 2026Margaret Kostyrko, Yuxuan Xue, Garvita Tiwari +1Non-Rigid Shape Correspondence3D Human Reconstruction

  25. Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation

    Sep 5, 2026Zhengyuan Li, Chuanyu Pan, Yuanming Hu +1Test-Time Augmentation3D Human Reconstruction

  26. Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation

    Sep 1, 2026Yuanwang Yang, Buzhen Huang, Zongxuan Ren +2Multi-View 3D Reconstruction3D Human Reconstruction