KelvinHong / pose-estimation-3d
Use a 2D Image to create 3D human model with a same pose. An integration of AlphaPose (2D pose estimation), MotionBert (2D Lift to 3D pose) and Blender (Armature Adjustment).
☆16Updated last year
Alternatives and similar repositories for pose-estimation-3d:
Users that are interested in pose-estimation-3d are comparing it to the libraries listed below
- Realtime Holistic Mocap with Ground Contact☆75Updated last year
- Official implementation of CVPR2022 paper "Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocul…☆104Updated 2 years ago
- Code of "NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation", CVPR 2023☆278Updated last year
- This repo equips the official CLIFF [ECCV 2022 Oral] with better detector, better tracker. Support multi-person, motion interpolation, mo…☆167Updated 2 years ago
- [CVPR 2023] Offical Pytorch implementation of "3D Human Mesh Estimation from Virtual Markers"☆266Updated last year
- Official Pytorch implementation for 2021 ICCV paper "Learning Motion Priors for 4D Human Body Capture in 3D Scenes" and trained models / …☆196Updated 11 months ago
- This repository contains an example script to convert from a SMPL model to a bvh file.☆170Updated last year
- Reproduce the work of the paper "Skeleton-Aware Networks for Deep Motion Retargeting" in Pytorch☆59Updated 4 years ago
- [TPAMI 2023] PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images☆249Updated 6 months ago
- Source code of the paper Scene-Aware 3D Multi-Human Motion Capture, EUROGRAPHICS 2023☆130Updated last year
- [CVPR 2023] Learning Analytical Posterior Probability for Human Mesh Recovery☆144Updated last year
- Load SMPL in blender☆317Updated last year
- Official PyTorch implementation of "Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation", CVPRW 2022 (Oral.)☆327Updated 5 months ago
- Code to reproduce the results for our SIGGRAPH 2023 paper "Listen Denoise Action"☆172Updated last year
- An Blender addon uses ROMP to extract human's 3D poses from image, video or webcam and drive your own 3D character.☆255Updated last year
- ☆53Updated 6 months ago
- codes for paper "Pose-aware Attention Network for Flexible Motion Retargeting by Body Part" (TVCG2023)