cure-lab/DeciWatch

[ECCV 2022] Official implementation of the paper "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"

38
/ 100
Emerging

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.

motion-capture human-computer-interaction gait-analysis sports-science animation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

189

Forks

15

Language

Python

License

Apache-2.0

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.