Cool-chic#
Cool-chic (pronounced /kul ʃik/ as in French 🥖🧀🍷) is a low-complexity neural image and video codec based on overfitting. Image coding performance are on par with VVC for 2000 multiplication per decoded pixels, while video coding performance compete with AVC with as few as 500 multiplication per decoded pixels.
Go to Cool-chic GitHub repository.
Version history#
- Fev. 24: version 3.1
Cool-chic video from Cool-chic video: Learned video coding with 800 parameters, Leguay et al.
Random access and low-delay video coding, competitive with AVC.
- January 24: version 3.0
Implement some encoder-side improvements from C3: High-performance and low-complexity neural compression from a single image or video, Kim et al
15% to 20% rate decrease compared to Cool-chic 2
- July 23: version 2
Based on Low-complexity Overfitted Neural Image Codec, Leguay et al.
Decoder changes: convolution-based synthesis, learnable upsampling module
Friendlier usage: support for YUV 420 input format in 8-bit and 10-bit & Fixed point arithmetic for cross-platform entropy (de)coding
- March 23: version 1
🏎️ 🔥 Up to come: a fast decoder implementation will be released soon for near real-time CPU decoding 🏎️ 🔥
Thanks#
Special thanks go to:
Robert Bamler for the constriction package which serves as our entropy coder. More details in Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician’s Perspective, Bamler.
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.