leoxiaobin/deep-high-resolution-net.pytorch
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
This project helps pinpoint key anatomical locations on people in images or video, often called human pose estimation. It takes an image or video frame as input and outputs precise coordinates for body joints like elbows, wrists, and ankles. Professionals in sports analytics, animation, robotics, or augmented reality would find this useful for analyzing or replicating human motion.
4,466 stars. No commits in the last 6 months.
Use this if you need highly accurate and spatially precise mapping of human body keypoints from visual data.
Not ideal if you need a lightweight model for real-time inference on low-power devices, or if your primary goal is general object detection rather than detailed pose analysis.
Stars
4,466
Forks
926
Language
Cuda
License
MIT
Category
Last pushed
Aug 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leoxiaobin/deep-high-resolution-net.pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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)