openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Science Score: 51.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org, scholar.google -
✓Committers with academic emails
1 of 14 committers (7.1%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.5%) to scientific vocabulary
Keywords
Repository
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
Basic Info
- Host: GitHub
- Owner: openpifpaf
- License: other
- Language: Python
- Default Branch: main
- Homepage: https://openpifpaf.github.io
- Size: 53.5 MB
Statistics
- Stars: 1,225
- Watchers: 32
- Forks: 253
- Open Issues: 50
- Releases: 66
Topics
Metadata Files
README.md
openpifpaf
Continuously tested on Linux, MacOS and Windows:
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.
Guide
Detailed documentation is in 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.
Examples
Image credit: "Learning to surf" by fotologic which is licensed under CC-BY-2.0.
Created with:
sh
pip3 install matplotlib openpifpaf
python3 -m openpifpaf.predict docs/coco/000000081988.jpg --image-output
Here is the tutorial for body, foot, face and hand keypoints. Example:
Image credit: Photo by Lokomotive74 which is licensed under CC-BY-4.0.
Created with:
sh
python -m openpifpaf.predict guide/wholebody/soccer.jpeg \
--checkpoint=shufflenetv2k30-wholebody --line-width=2 --image-output
Here is the tutorial for car keypoints. Example:
Image credit: Photo by Ninaras which is licensed under CC-BY-SA 4.0.
Created with:
sh
python -m openpifpaf.predict guide/images/peterbourg.jpg \
--checkpoint shufflenetv2k16-apollo-24 -o images \
--instance-threshold 0.05 --seed-threshold 0.05 \
--line-width 4 --font-size 0
Here is the tutorial for animal keypoints (dogs, cats, sheep, horses and cows). Example:
sh
python -m openpifpaf.predict guide/images tappo_loomo.jpg \
--checkpoint=shufflenetv2k30-animalpose \
--line-width=6 --font-size=6 --white-overlay=0.3 \
--long-edge=500
Commercial License
The open source license is in the LICENSE file. This software is also available for licensing via the EPFL Technology Transfer Office (https://tto.epfl.ch/, info.tto@epfl.ch).
Owner
- Name: OpenPifPaf
- Login: openpifpaf
- Kind: organization
- Repositories: 4
- Profile: https://github.com/openpifpaf
Citation (citation.bib)
@article{kreiss2021openpifpaf,
title = {{OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association}},
author = {Sven Kreiss and Lorenzo Bertoni and Alexandre Alahi},
journal = {arXiv preprint arXiv:2103.02440},
month = {March},
year = {2021}
}
GitHub Events
Total
- Issues event: 3
- Watch event: 50
- Issue comment event: 1
- Fork event: 4
Last Year
- Issues event: 3
- Watch event: 50
- Issue comment event: 1
- Fork event: 4
Committers
Last synced: 8 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Sven Kreiss | me@s****m | 1,607 |
| Sven Kreiss | s****s@e****h | 31 |
| DuncanZauss | 5****s | 13 |
| Lorenzo Bertoni | 3****9 | 8 |
| David Mizrahi | 3****r | 5 |
| mdenna | m****a@n****h | 3 |
| george-adaimi | g****i@g****m | 2 |
| simejanko | s****o | 1 |
| junedgar | j****0@1****m | 1 |
| cuong20150532 | c****g@a****t | 1 |
| Taylor Mordan | 4****n | 1 |
| Lilian Mallardeau | l****u@g****m | 1 |
| Krishna Kanth | 3****a | 1 |
| Jiawei Liu | j****u@g****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 4 months ago
All Time
- Total issues: 88
- Total pull requests: 47
- Average time to close issues: about 1 month
- Average time to close pull requests: 3 days
- Total issue authors: 77
- Total pull request authors: 8
- Average comments per issue: 1.57
- Average comments per pull request: 0.98
- Merged pull requests: 35
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 3
- Pull requests: 0
- Average time to close issues: 13 minutes
- Average time to close pull requests: N/A
- Issue authors: 3
- Pull request authors: 0
- Average comments per issue: 0.33
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- SoumyajitMukherjee-droid (3)
- ljxxxxxxxxxxxx (3)
- grayskripko (2)
- JSVJ (2)
- njho (2)
- cwlinghk (2)
- tijanavukovic1 (2)
- zhangjiekui (2)
- xenagarage (2)
- WhaSukGO (1)
- taylormordan (1)
- bach05 (1)
- sercharpak (1)
- Agustin6199 (1)
- creating-worlds (1)
Pull Request Authors
- svenkreiss (34)
- AleksandrSim (14)
- iamragha (2)
- simejanko (1)
- krishnakanthnakka (1)
- lilianmallardeau (1)
- AK391 (1)
- corey-nm (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 2,583 last-month
- Total docker downloads: 60
- Total dependent packages: 6
- Total dependent repositories: 22
- Total versions: 64
- Total maintainers: 1
pypi.org: openpifpaf
PifPaf: Composite Fields for Human Pose Estimation
- Homepage: https://github.com/openpifpaf/openpifpaf
- Documentation: https://openpifpaf.readthedocs.io/
- License: GNU AGPLv3
-
Latest release: 0.13.11
published almost 3 years ago
Rankings
Maintainers (1)
Dependencies
- dataclasses *
- importlib_metadata *
- numpy >=1.16
- pillow *
- pysparkling *
- python-json-logger *
- torch ==1.11.0
- torchvision ==0.12.0
- FedericoCarboni/setup-ffmpeg v2 composite
- actions/cache v3 composite
- actions/checkout v3 composite
- actions/setup-python v1 composite
- peaceiris/actions-gh-pages v3 composite
- FedericoCarboni/setup-ffmpeg v2 composite
- actions/cache v3 composite
- actions/checkout v3 composite
- actions/setup-python v1 composite
- peaceiris/actions-gh-pages v3 composite
- actions/checkout v3 composite
- actions/download-artifact v3 composite
- actions/setup-python v4 composite
- actions/upload-artifact v3 composite
- pypa/gh-action-pypi-publish release/v1 composite
- FedericoCarboni/setup-ffmpeg v2 composite
- actions/cache v3 composite
- actions/checkout v3 composite
- actions/setup-python v4 composite
- s-weigand/setup-conda v1 composite
- actions/checkout v3 composite