mks0601/3DMPPE_ROOTNET_RELEASE
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
This project helps researchers and developers working with human motion analysis by taking standard RGB images or video frames and determining the 3D position of key body joints for multiple people in the scene. It specifically focuses on accurately estimating the root joint (pelvis) in 3D space, which is crucial for overall pose estimation. It is ideal for those who need precise 3D human pose data from everyday camera footage.
490 stars. No commits in the last 6 months.
Use this if you need to precisely estimate the 3D position of multiple people's body joints from standard camera images, especially for research in human activity recognition or biomechanics.
Not ideal if you are looking for a simple, off-the-shelf application for casual use or if your primary interest is 2D pose detection without the depth component.
Stars
490
Forks
66
Language
Python
License
MIT
Category
Last pushed
Jul 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/mks0601/3DMPPE_ROOTNET_RELEASE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.