DenisTome/Lifting-from-the-Deep-release
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"
This project helps computer vision researchers and developers estimate human body posture in 3D from a single standard image. You provide an image containing a person, and it outputs the estimated 3D positions of their body joints. This is useful for researchers working on human activity recognition, augmented reality, or robotics.
450 stars. No commits in the last 6 months.
Use this if you need to accurately determine the 3D pose of a person from a single photograph or video frame.
Not ideal if you require real-time performance on constrained hardware or need to estimate poses from multiple camera angles for greater accuracy.
Stars
450
Forks
133
Language
Python
License
GPL-3.0
Category
Last pushed
Jan 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DenisTome/Lifting-from-the-Deep-release"
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
CMU-Perceptual-Computing-Lab/openpose_train
Training repository for OpenPose