akashsengupta1997/HierarchicalProbabilistic3DHuman
Code repository for the paper: Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild (ICCV 2021)
This project helps researchers analyze human motion by reconstructing detailed 3D body shapes and poses from standard 2D images. You input a picture of a person, and it outputs multiple likely 3D models showing their body shape and posture, including an estimation of how uncertain the model is. It's designed for researchers working on understanding and modeling human movement.
204 stars. No commits in the last 6 months.
Use this if you are a researcher needing to convert 2D images of people into accurate 3D kinematic models for analysis, especially when considering multiple plausible poses.
Not ideal if you need real-time performance for live applications or if you are not comfortable with command-line tools and academic-style software.
Stars
204
Forks
12
Language
Python
License
MIT
Category
Last pushed
Feb 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/akashsengupta1997/HierarchicalProbabilistic3DHuman"
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)