3d-human-mesh 开源项目推荐（25 个）

wangzheallen /awesome-human-pose-estimation

人体姿势估计相关出版物

hongsukchoi /Pose2Mesh_RELEASE

Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020

isarandi /nlf

[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

DavidBoja /SMPL-Anthropometry

测量SMPL体模型

hongsukchoi /TCMR_RELEASE

Official Pytorch implementation of "Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video", CVPR 2021

mkocabas /SPEC

Code for ICCV2021 paper SPEC: Seeing People in the Wild with an Estimated Camera

isarandi /smplfitter

The Fast Way From Vertices to Parametric 3D Humans

muelea /buddi

Our model BUDDI learns the joint distribution of interacting people

hongsukchoi /3DCrowdNet_RELEASE

Official Pytorch implementation of "Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes", CVPR 2022

luyangzhu /NBA-Players

ECCV2020 - Official code repository for the paper : Reconstructing NBA Players

luyangzhu /NBA2K-dataset

ECCV2020论文的NBA2K数据集：重建NBA球员

Intellindust-AI-Lab /SKEL-CF

[ECCV 2026] Pytorch implementation of "SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery"

xuxy09 /RSC-Net

Implementation for "3D human pose, shape and texture from low-resolution images and videos", TPAMI 2021

sanweiliti /PLACE

Official Pytorch implementation for 2020 3DV paper "PLACE: Proximity Learning of Articulation and Contact in 3D Environments" and trained models

wangkua1 /nemo-cvpr2023

[CVPR 2023 Highlight] Official implementation of "NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action"

zjwfufu /EVA-Tracker

[CVPR 2026] A versatile toolbox for human mesh estimation

RCHI-Lab /BodyMAP

Official implementation of "BodyMAP - Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bed", CVPR 2024

tharuneshwar-s /body-measurement-to-smpl-beta

This project was born out of a passion for computer vision and 3D human modeling. It explores the power of SMPLX for body shape representation and demonstrates its application in generating realistic 3D avatars from simple measurements.

kristijanbartol /linear-3d-humans

"Linear Regression vs. Deep Learning". The source code for a simple but effective baseline method for human body measurement estimation using only height and weight information about the person.

WhitKey /soma2amass

SEED / SOMA (MHR) BVH mocap to AMASS-format SMPL-X .npz. Retargets through the SOMA-X rig and a topology bridge, then fits SMPL-X with smplfitter.