InterDigitalInc/CompressAI-Vision

CompressAI-Vision helps you design, test and compare Video Compression for Machines pipelines. Compression methods can be either pulled from custom AI-based modules from CompressAI or traditional codecs such as H.266/VVC.

46
/ 100
Emerging

This tool helps researchers and engineers evaluate how well video and intermediate visual features are compressed when used for machine tasks like object detection or pose estimation. You feed it video or feature data, along with different compression methods (both traditional and AI-based), and it outputs performance metrics for computer vision tasks. This is for anyone working on optimizing data transmission for AI-driven video analysis.

113 stars.

Use this if you need to compare and test various video or feature compression techniques specifically for how they impact machine vision algorithms, such as those used in remote inference or split model deployments.

Not ideal if you are looking for a general-purpose video compressor for human viewing or a tool for developing new machine learning models from scratch.

video-analytics computer-vision edge-AI machine-learning-operations data-compression
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

113

Forks

10

Language

Python

License

BSD-3-Clause-Clear

Last pushed

Jan 29, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/InterDigitalInc/CompressAI-Vision"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.