Cool-chic (pronounced /kul ʃik/ as in French 🥖🧀🍷) is a low-complexity neural image codec based on overfitting. It offers coding performance on par with H.266/VVC for 1000 multiplications per decoded pixel, allowing for fast CPU-only decoding.

Docs What’s new in 3.4? Decode some bitstreams Coding performance

Great coding performance

Cool-chic compresses images as well as H.266/VVC

https://orange-opensource.github.io/Cool-Chic/results/image/compression_performance.html

Lightweight decoder

Cool-chic decoder only computes 1000 multiplications per decoded pixel

https://orange-opensource.github.io/Cool-Chic/results/image/decoding_complexity.html

Fast CPU-only decoder

Decode a 1280x720 image in 100 ms on CPU with our decoder written in C

https://orange-opensource.github.io/Cool-Chic/results/image/decoding_complexity.html

I/O format

Encode PNG, PPM and YUV 420 & 444 files with a bitdepth of 8 to 16 bits.

https://orange-opensource.github.io/Cool-Chic/encoding/overview.html#i-o-format

Special thanks to Hyunjik Kim, Matthias Bauer, Lucas Theis, Jonathan Richard Schwarz and Emilien Dupont for their great work enhancing Cool-chic: C3: High-performance and low-complexity neural compression from a single image or video, Kim et al.