ibaiGorordo/Sapiens-Pytorch-Inference
Minimal code and examnples for inferencing Sapiens foundation human models in Pytorch
This tool helps researchers and computer vision practitioners automatically analyze human figures in images and videos. It takes an input image or video containing people and outputs detailed maps showing human depth, surface normals, and segmented body parts. It's ideal for anyone working on projects requiring precise understanding of human pose and form.
155 stars.
Use this if you need to extract detailed 3D-aware information about human figures, such as their orientation or how far they are from the camera, directly from standard 2D footage.
Not ideal if you require very high accuracy from cropped images of people, or if processing speed with ONNX models is your primary concern.
Stars
155
Forks
16
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ibaiGorordo/Sapiens-Pytorch-Inference"
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"