[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

[CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"

ECCV2020 - Official code repository for the paper : STAR - A Sparse Trained Articulated Human Body Regressor

ExPose - EXpressive POse and Shape rEgression

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

[ICML 2024] 🍅HumanTOMATO: Text-aligned Whole-body Motion Generation

[TPAMI 2023] PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images

The Fast Way From Vertices to Parametric 3D Humans

Our model BUDDI learns the joint distribution of interacting people

(ECCV 2024) SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

[CVPR 2024] AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion

[ICCV 2025 Highlight] ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness

Fit an SMPL body model to a scan

Towards Robust 3D Body Mesh Inference of Partially-observed Humans: semester project at ETH Zurich

Smplify-X implementation. (2025. 04. 07 No Error & Recent version)

Official PyTorch implementation of BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025). BLADE tackles close-range human mesh recovery where perspective distortion is strongest, and solves for camera pose and focal length in addition to SMPL(-X) parameters.

OpenXRLab GPU Cloth Simulation Engine

Fine-tuned LLMs generate accurate 3D human avatars from textual descriptions using the SMPL-X model, enhancing customization and simulation in virtual environments.

[ECCV 24 wksp] Pose-independent 3D Anthropometry from Sparse Data

A simple SMPL library

Code to construct textured deformed SMPL-X meshes for HUMBI data

AR visualization of The Wanderings of Odysseus

一个基于 Web 的交互式 3D 人体姿态可视化和编辑工具，支持 SMPL/SMPLX 模型格式，提供直观的姿态调节界面

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.

import mocap data into blender

A 100% compatiable SMPL,SMPL-H,SMPL-X model implemention in C++ with CUDA support. Same api with python smplx.

Simple 3D rendering of hand-object interactions for the ARCTIC dataset

This repo contains a UI that captures 360 deg video of a user and sends it to 2 servers. Model server extracts the 3d reconstruction and measurements of user. Base server saves this data

3D aware implicit Generative Adversarial Network