ziniuwan/maed
[ICCV 2021] Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation
This project helps researchers and engineers accurately reconstruct 3D human shape and pose from video footage. It takes standard video clips as input and outputs precise 3D models of human movement and body shape, useful for applications like sports analysis, animation, or medical diagnostics. This is ideal for those working with human motion capture and analysis.
209 stars. No commits in the last 6 months.
Use this if you need to derive accurate 3D human body shape and detailed pose estimations from regular video recordings.
Not ideal if you are looking for a plug-and-play solution without expertise in machine learning model training and evaluation.
Stars
209
Forks
20
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ziniuwan/maed"
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.