3D Human Reconstruction

Follow this topic Ask about this topic

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

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

MultiGO++: Monocular 3D Clothed Human Reconstruction via Geometry-Texture Collaboration
Mar 5, 2026Nanjie Yao, Gangjian Zhang, Wenhao Shen +33D Reconstruction Monocular 3D Reconstruction
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511442, China · Nanyang Technological University, Singapore 639798
DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
Mar 3, 2026Yufu Wang, Evonne Ng, Soyong Shin +83D Human Motion Reconstruction 3D Human Reconstruction
Meta Reality Labs · University of Pennsylvania · Carnegie Mellon University
Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting
Mar 3, 2026Kaiqiang Xiong, Rui Peng, Jiahao Wu +5Multi-View Diffusion Models 3D Human Reconstruction
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University · Peng Cheng Laboratory · Alibaba Group +2
Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
Mar 3, 2026Seunguk Do, Minwoo Huh, Joonghyuk Shin +1Multi-View Diffusion Models 3D Human Reconstruction
Seoul National University
Biomechanically Accurate Gait Analysis: A 3d Human Reconstruction Framework for Markerless Estimation of Gait Parameters
Mar 3, 2026Akila Pemasiri, Ethan Goan, Glen Lichtwark +3Musculoskeletal Modeling Gait Analysis
Queensland University of Technology, Brisbane · Griffith University, Gold Coast
HumanOrbit: 3D Human Reconstruction as 360° Orbit Generation
Feb 27, 2026Keito Suzuki, Kunyao Chen, Lei Wang +5Multi-View Image Synthesis 3D Human Reconstruction
University of California, San Diego · Qualcomm
Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates
Feb 27, 2026Yingxuan You, Ren Li, Corentin Dumery +33D Garment Reconstruction 3D Reconstruction
CVLab, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland · Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates · Pinscreen and Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates
AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors
Feb 27, 2026Xiaozhen Qiao, Wenjia Wang, Zhiyuan Zhao +43D Human Reconstruction Feed-Forward 3D Reconstruction
Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China. · University of Science and Technology of China. · University of Hong Kong. +1
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents
Feb 26, 2026Wenjia Wang, Liang Pan, Huaijin Pi +83D Human Reconstruction Embodied AI
The University of Hong Kong · Tampere University · The Chinese University of Hong Kong +1
TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures
Feb 23, 2026Hyeongjin Nam, Daniel Sungho Jung, Kyoung Mu Lee3D Reconstruction 3D Human Reconstruction
Dept. of ECE&ASRI, Seoul National University · IPAI, Seoul National University
VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery
Feb 22, 2026Wenhao Shen, Hao Wang, Wanqi Yin +5Human Mesh Recovery 3D Human Reconstruction
Nanyang Technological University · HKUST(GZ) · SenseTime Research +1
MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation
Nov 24, 2025Farnoosh Koleini, Hongfei Xue, Ahmed Helmy +1Markerless Motion Capture Musculoskeletal Modeling
University of North Carolina at Charlotte
MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images
Jun 11, 2025Chentao Song, He Zhang, Haolei Yuan +4Metric Depth Estimation 3D Reconstruction
Tsinghua University · Beihang University · Beijing Normal University
Sonicmesh: Enhancing 3D Human Mesh Reconstruction in Vision-Impaired Environments With Acoustic Signals
Dec 15, 2024Xiaoxuan Liang, Hong Zhou, Zhaolong Wei +33D Reconstruction Human Mesh Recovery
University of Massachusetts at Amherst, Location, Country · Trine University · University of Illinois at Chicago +1
PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
Sep 16, 2024Peng Li, Wangguandong Zheng, Yuan Liu +9Multi-View Diffusion Models 3D Reconstruction
HKUST · Southeast University · Tsinghua University +1

Mar 5, 2026J/K move · Enter open · S save

MultiGO++: Monocular 3D Clothed Human Reconstruction via Geometry-Texture Collaboration

Nanjie Yao, Gangjian Zhang, Wenhao Shen, Jian Shu+2

The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511442, China · Nanyang Technological University, Singapore 639798

3D Reconstruction Monocular 3D Reconstruction 3D Human Reconstruction 3D Mesh Reconstruction

Open paper AskPDF arXiv

Monocular 3D clothed human reconstruction aims to generate a complete and realistic textured 3D avatar from a single image. Existing methods are commonly trained under multi-view supervision with annotated geometric priors, and during inference, these priors are estimated by the pre-trained network from the monocular input. These methods are constrained by three key limitations: texturally by unavailability of training data, geometrically by inaccurate external priors, and systematically by biased single-modality supervision, all leading to suboptimal reconstruction. To address these issues, we propose a novel reconstruction framework, named MultiGO++, which achieves effective systematic geometry-texture collaboration. It consists of three core parts: (1) A multi-source texture synthesis strategy that constructs 15,000+ 3D textured human scans to improve the performance on texture quality estimation in challenge scenarios; (2) A region-aware shape extraction module that extracts and interacts features of each body region to obtain geometry information and a Fourier geometry encoder that mitigates the modality gap to achieve effective geometry learning; (3) A dual reconstruction U-Net that leverages geometry-texture collaborative features to refine and generate high-fidelity textured 3D human meshes. Extensive experiments on two benchmarks and many in-the-wild cases show the superiority of our method over state-of-the-art approaches.