Cool-chic (pronounced /kul Κik/ as in French π₯π§π·) is a low-complexity neural image codec based on overfitting. It offers image coding performance competitive with H.266/VVC for 2000 multiplications per decoded pixel.
Current & future featuresΒΆ
β¬ Coding performance - β On par with VVC for image coding - β Upcoming improved Cool-chic video β¬ I/O format - β PPM for 8-bit RGB images, yuv420 8-bit and 10-bit - β yuv444 - β Additional output precisions (12, 14 and 16-bit) - β Output PNG instead of PPM for the decoded images β¬ Decoder - β Fast C implementation - β Integer computation ARM - β Complete integerization - β Decrease memory footprint & faster decodingCool-chic 3.3 improvementsΒΆ
Make the CPU-only decoder even faster
Decode a 720p image in 100 ms, 2x faster than Cool-chic 3.2
Full integerization of the decoder for replicability
Reduce decoder memory footprint
Optimized implementation of 3x3 convolutions & fusion of successive 1x1 convolutions
Check-out the release history to see previous versions of Cool-chic.
Attention
π Cool-chic 3.3 temporarily disables video coding. If you really want to compress videos you can
Go back to 3.1:
git clone --branch v3.1 https://github.com/Orange-OpenSource/Cool-Chic.git
Wait for Cool-chic 4.0 for better and faster video coding π.
ThanksΒΆ
Special thanks go 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.