ZiyiZhang27/Dite-HRNet
[IJCAI 2022] Code for the paper "Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation"
This project helps quickly and accurately identify and locate human body joints in images, known as human pose estimation. It takes an image or video frame as input and outputs the precise coordinates of key body points, even in complex scenarios. This tool is designed for computer vision researchers and engineers working on applications like human-computer interaction, sports analysis, or action recognition.
No commits in the last 6 months.
Use this if you need a lightweight yet highly accurate model for identifying human keypoints in various image resolutions.
Not ideal if your application requires real-time processing on very resource-constrained edge devices without GPU acceleration.
Stars
78
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ZiyiZhang27/Dite-HRNet"
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
DenisTome/Lifting-from-the-Deep-release
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"