sithu31296/pose-estimation
Easy to use SOTA Top-Down Multi-person Pose Estimation Models in PyTorch
This tool helps you analyze images or video footage to precisely locate and track the main joints (like elbows, knees, or head) of every person present. You provide an image or video, and it outputs a visual representation of these "keypoints" on each individual. It's ideal for researchers studying human movement, animators, or anyone needing detailed posture analysis.
No commits in the last 6 months.
Use this if you need highly accurate body joint detection for multiple people in images or videos, even when computational intensity is acceptable for better precision.
Not ideal if you prioritize speed and efficiency over the highest possible accuracy for person keypoint detection, or if you only need to identify people without detailed joint analysis.
Stars
54
Forks
13
Language
Python
License
MIT
Category
Last pushed
Sep 18, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sithu31296/pose-estimation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
kenshohara/3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)