3D Human Reconstruction

Ask about this topic

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

105 papers14 papers in the last four weeks, up 40% on the four weeks before. 0.1% of all new papers.

  1. Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

    May 5, 2026Evangelos Ntavelis, Sean Wu, Mohamad Shahbazi +213D Gaussian SplattingMulti-View 3D Reconstruction

    Apple

  2. 3D Human Face Reconstruction with 3DMM face model from RGB image

    May 5, 2026Zhangnan Jiang, Zichen Yang3D Morphable Models3D Mesh Reconstruction

    Tandon School of Engineering New York University

  3. HumanSplatHMR: Closing the Loop Between Human Mesh Recovery and Gaussian Splatting Avatar

    May 4, 2026Yeheng Zong, Pou-Chun Kung, Yike Pan +43D ReconstructionHuman Mesh Recovery

    University of Michigan

  4. High-Fidelity Mobile Avatars with Pruned Local Blendshapes

    May 3, 2026Youyi Zhan, He Wang, Tianjia Shao +1Model Compression3D Gaussian Splatting

    State Key Lab of CAD&CG, Zhejiang University · University College London

  5. ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss

    Apr 30, 2026Jiaying Ying, Heming Du, Kaihao Zhang +23D ReconstructionHuman Mesh Recovery

    The University of Queensland · Australian National University · The University of Adelaide

  6. OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

    Apr 23, 2026Zeyu Cai, Yuliang Xiu, Renke Wang +83D ReconstructionHuman Mesh Recovery

    Nanjing University · Westlake University · Nanjing University of Science and Technology +2

  7. LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image

    Apr 22, 2026Dimitrije Antić, Alvaro Budria, George Paschalidis +23D ReconstructionVector-Quantized Variational Autoencoder

    University of Amsterdam, The Netherlands · Max Planck Institute for Intelligent Systems, Tübingen, Germany · Aristotle University of Thessaloniki, Greece

  8. UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video

    Apr 21, 2026Tanuj Sur, Shashank Tripathi, Nikos Athanasiou +44D ReconstructionHuman Mesh Recovery

    1National University of Singapore · 2Max Planck Institute for Intelligent Systems, Tübingen, Germany

  9. GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction

    Apr 21, 2026Pradyumna YM, Yuxuan Xue, Yue Chen +33D ViTs3D Reconstruction

    University of Tübingen · Tübingen AI Center · Westlake University +1

  10. Discriminative-Generative Synergy for Occlusion Robust 3D Human Mesh Recovery

    Apr 20, 2026Yang Liu, Zhiyong Zhang3D ReconstructionHuman Mesh Recovery

    School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, Guangdong, China

  11. AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion

    Apr 20, 2026Hongjie Li, Heng Yu, Jiaman Li +4Markerless Motion Capture3D Reconstruction

    Stanford University · H. Li is now with Peking University

  12. CLOTH-HUGS: Cloth Aware Human Gaussian Splatting

    Apr 17, 2026Sadia Mubashshira, Nazanin Amini, Kevin Desai3D Gaussian Splatting3D Reconstruction

  13. SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance

    Apr 15, 2026Qi Xia, Peishan Cong, Ziyi Wang +63D Human ReconstructionMonocular 3D Reconstruction

    ShanghaiTech University · Nanyang Technological University · Guangzhou Institute of Energy Conversion, CAS +4

  14. Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting

    Apr 11, 2026Devdoot Chatterjee, Zakaria Laskar, C. V. Jawahar3D Human ReconstructionHuman Avatar Animation

    IIIT Hyderabad, India · IISER Thiruvananthapuram, India

  15. F3G-Avatar : Face Focused Full-body Gaussian Avatar

    Apr 10, 2026Willem Menu, Erkut Akdag, Pedro Quesado +23D Avatar Generation3D Human Reconstruction

    AIMS Group, Department of Electrical Engineering, Eindhoven University of Technology

  16. Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction

    Apr 10, 2026Yuze Su, Hongsong Wang, Jie Gui +13D Hand Reconstruction3D Human Reconstruction

    School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China · School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China +5

  17. Human Interaction-Aware 3D Reconstruction from a Single Image

    Apr 7, 2026Gwanghyun Kim, Junghun James Kim, Suh Yoon Jeon +23D Human ReconstructionSingle-View 3D Reconstruction

    Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea · IPAI, Seoul National University, Republic of Korea · INMC, Seoul National University, Republic of Korea

  18. HOIGS: Human-Object Interaction Gaussian Splatting

    Apr 5, 2026Taewoo Kim, Suwoong Yeom, Jaehyun Pyun +6Human-Scene Interaction Reconstruction3D Reconstruction

    Department of Electronics Engineering, Sogang University, South Korea · NAVER Cloud Corp, South Korea · Department of Electrical & Electronics Engineering, Pusan National University, South Korea

  19. Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining

    Apr 2, 2026Junxuan Li, Rawal Khirodkar, Chengan He +373D Avatar Generation3D Human Reconstruction

    Codec Avatars Lab, Meta

  20. Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars

    Apr 1, 2026Derek Austin3D Avatar Generation3D Human Reconstruction

  21. Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery

    Apr 1, 2026Minghao Sun, Chongyang Xu, Yitao Xie +23D Reconstruction3D Human Reconstruction

    Tianjin University · Nanyang Technological University · Sichuan University

  22. GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates

    Mar 30, 2026Youngjoong Kwon, Yao He, Heejung Choi +43D Human ReconstructionNovel View Synthesis

    Stanford University

  23. Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields

    Mar 26, 2026Thanh-Hai Le, Hoang-Hau Tran, Trong-Nghia VuNeural Radiance FieldsSparse-View 3D Reconstruction

    School of Computer Science and Engineering, The Saigon International University, Ho Chi Minh City 700000, Vietnam · Department of Informatic Technology, FPT University, Ho Chi Minh City 700000, Vietnam

  24. GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems

    Mar 19, 2026Xiaojian Lin, Yaomin Shen, Junyuan Ma +73D Human Reconstruction

    Tsinghua University, China · XR System Application Research Center, Nanchang Research Institute, Zhejiang University, China · Beijing University of Posts and Telecommunications, China +2

  25. CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image

    Mar 18, 2026Yizheng Song, Yiyu Zhuang, Qipeng Xu +53D Human ReconstructionSingle-View 3D Reconstruction

    Nanjing University, China · State Key Laboratory of Novel Software Technology, China · Fudan University, China

  26. Real-Time Human Frontal View Synthesis from a Single Image

    Mar 16, 2026Fangyu Lin, Yingdong Hu, Lunjie Zhu +4Novel View Synthesis3D Human Reconstruction

    HKUST, Hong Kong SAR, China

  27. End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction

    Mar 15, 2026Haoyu Zhang, Wei Zhai, Yuhang Yang +2Spatiotemporal Transformers4D Reconstruction

    University of Science and Technology of China

  28. OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images

    Mar 15, 2026Yuanwang Yang, Hongliang Liu, Muxin Zhang +43D ReconstructionMonocular 3D Reconstruction

    College of Intelligence and Computing, Tianjin University, Tianjin 300350, China · College of Artificial Intelligence, Beijing University of Technology, Beijing 100124, China · School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China +1

  29. HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstruction

    Mar 13, 2026Sangmin Kim, Minhyuk Hwang, Geonho Cha +23D ReconstructionMulti-View 3D Reconstruction

    Seoul National University · NAVER Cloud

  30. Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capture

    Mar 10, 2026Tom Wehrbein, Bodo RosenhahnMarkerless Motion Capture3D Human Reconstruction

    L3S - Leibniz University Hannover, Germany