Skip to main content

PifPaf: Composite Fields for Human Pose Estimation

Project description

openpifpaf

Continuously tested on Linux, MacOS and Windows: Tests deploy-guide Downloads
New 2021 paper:

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association
Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi, 2021.

Many image-based perception tasks can be formulated as detecting, associating and tracking semantic keypoints, e.g., human body pose estimation and tracking. In this work, we present a general framework that jointly detects and forms spatio-temporal keypoint associations in a single stage, making this the first real-time pose detection and tracking algorithm. We present a generic neural network architecture that uses Composite Fields to detect and construct a spatio-temporal pose which is a single, connected graph whose nodes are the semantic keypoints (e.g., a person's body joints) in multiple frames. For the temporal associations, we introduce the Temporal Composite Association Field (TCAF) which requires an extended network architecture and training method beyond previous Composite Fields. Our experiments show competitive accuracy while being an order of magnitude faster on multiple publicly available datasets such as COCO, CrowdPose and the PoseTrack 2017 and 2018 datasets. We also show that our method generalizes to any class of semantic keypoints such as car and animal parts to provide a holistic perception framework that is well suited for urban mobility such as self-driving cars and delivery robots.

Previous CVPR 2019 paper.

Example

example image with overlaid pose predictions

Image credit: "Learning to surf" by fotologic which is licensed under CC-BY-2.0.
Created with:

pip3 install openpifpaf matplotlib
python3 -m openpifpaf.predict docs/coco/000000081988.jpg --image-min-dpi=200 --show-file-extension=jpeg --image-output

Guide

Continue to our OpenPifPaf Guide.

For developers, there is also the DEV Guide which is the same guide but based on the latest code in the main branch.

Commercial License

This software is available for licensing via the EPFL Technology Transfer Office (https://tto.epfl.ch/, info.tto@epfl.ch).

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for openpifpaf, version 0.12.9
Filename, size File type Python version Upload date Hashes
Filename, size openpifpaf-0.12.9-cp36-cp36m-macosx_10_9_x86_64.whl (280.3 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp36-cp36m-manylinux1_i686.whl (709.4 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp36-cp36m-manylinux2014_i686.whl (709.4 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp36-cp36m-manylinux2014_x86_64.whl (740.5 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp36-cp36m-win32.whl (262.5 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp36-cp36m-win_amd64.whl (283.4 kB) File type Wheel Python version cp36 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp37-cp37m-macosx_10_9_x86_64.whl (280.5 kB) File type Wheel Python version cp37 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp37-cp37m-manylinux1_i686.whl (710.4 kB) File type Wheel Python version cp37 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp37-cp37m-manylinux2014_i686.whl (710.4 kB) File type Wheel Python version cp37 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp37-cp37m-manylinux2014_x86_64.whl (740.3 kB) File type Wheel Python version cp37 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp37-cp37m-win32.whl (262.4 kB) File type Wheel Python version cp37 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp37-cp37m-win_amd64.whl (283.5 kB) File type Wheel Python version cp37 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp38-cp38-macosx_10_9_x86_64.whl (280.8 kB) File type Wheel Python version cp38 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp38-cp38-manylinux1_i686.whl (767.0 kB) File type Wheel Python version cp38 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp38-cp38-manylinux2014_i686.whl (767.0 kB) File type Wheel Python version cp38 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp38-cp38-manylinux2014_x86_64.whl (794.4 kB) File type Wheel Python version cp38 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp38-cp38-win32.whl (264.8 kB) File type Wheel Python version cp38 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp38-cp38-win_amd64.whl (284.9 kB) File type Wheel Python version cp38 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-macosx_10_9_universal2.whl (378.6 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-macosx_10_9_x86_64.whl (283.2 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-macosx_11_0_arm64.whl (271.9 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-manylinux1_i686.whl (744.2 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-manylinux2014_i686.whl (744.2 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-manylinux2014_x86_64.whl (778.1 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-win32.whl (265.0 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9-cp39-cp39-win_amd64.whl (285.0 kB) File type Wheel Python version cp39 Upload date Hashes View
Filename, size openpifpaf-0.12.9.tar.gz (295.4 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page