cure-lab/DeciWatch
[ECCV 2022] Official implementation of the paper "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"
This project helps video analysis practitioners quickly and efficiently estimate human pose and body shapes from video footage. It takes existing 2D/3D pose estimation results for a subset of video frames and intelligently fills in the gaps for the remaining frames. The output includes highly accurate and smooth 2D poses, 3D poses, or full 3D body models (SMPL), making it ideal for researchers and professionals analyzing human motion.
189 stars. No commits in the last 6 months.
Use this if you need to perform high-quality 2D or 3D human pose estimation or body shape recovery from videos, but want to significantly reduce the computational time and resources required.
Not ideal if you are working with static images or if your primary need is for a brand-new pose estimation model rather than improving the efficiency of existing methods.
Stars
189
Forks
15
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cure-lab/DeciWatch"
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.