CalciferZh/minimal-body
A very simple baseline to estimate 2D & 3D SMPL-compatible keypoints from a single color image.
This tool helps researchers and computer vision practitioners analyze human body posture and movement from single images. You provide an image of a person, and it outputs a set of 2D and 3D keypoints representing their body joints. This is useful for anyone working with human pose estimation in various applications.
No commits in the last 6 months.
Use this if you need to quickly and efficiently estimate human body keypoints in both 2D and 3D from a single, cropped portrait image.
Not ideal if you require training code, high-accuracy estimations from uncropped or complex scenes, or detailed mesh reconstruction rather than just keypoints.
Stars
58
Forks
6
Language
Python
License
MIT
Category
Last pushed
Nov 20, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/CalciferZh/minimal-body"
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.