InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
CompressAI helps researchers and engineers working on media compression develop and evaluate new, highly efficient image and video compression techniques. You can input raw image or video data and use this to compare your custom compression models against established methods like BPG or VTM, or explore pre-trained AI models for state-of-the-art results. This is for anyone creating or comparing advanced compression algorithms.
1,535 stars. Actively maintained with 20 commits in the last 30 days. Available on PyPI.
Use this if you are developing new deep learning-based methods for image or video compression and need a robust framework to build, train, and benchmark your models.
Not ideal if you simply need to compress media files for everyday use or are looking for a user-friendly application rather than a research toolkit.
Stars
1,535
Forks
266
Language
Python
License
BSD-3-Clause-Clear
Category
Last pushed
Mar 12, 2026
Commits (30d)
20
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/InterDigitalInc/CompressAI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)
zhanghang1989/PyTorch-Encoding
A CV toolkit for my papers.