# Cool-Chic **Repository Path**: housz77/Cool-Chic ## Basic Information - **Project Name**: Cool-Chic - **Description**: No description available - **Primary Language**: Unknown - **License**: BSD-3-Clause - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2024-12-27 - **Last Updated**: 2024-12-27 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README [![Contributors][contributors-shield]][contributors-url] [![Forks][forks-shield]][forks-url] [![Stargazers][stars-shield]][stars-url] [![Issues][issues-shield]][issues-url] [![BSD-3 License][license-shield]][license-url] [![PyTorch][pytorch-shield]][pytorch-url]
Cool-chic Logo


Explore the docs ยป

What's new in 3.4? ยท Decode some bitstreams ยท Coding performance

Cool-chic (pronounced /kul สƒik/ as in French ๐Ÿฅ–๐Ÿง€๐Ÿท) is a low-complexity neural image codec based on overfitting. It offers image coding performance competitive with **H.266/VVC for 1000 multiplications** per decoded pixel.
#### ๐Ÿ† **Coding performance**: Cool-chic compresses images as well as H.266/VVC ๐Ÿ† #### ๐Ÿš€ **Fast CPU-only decoder**: Decode a 1280x720 image in 100 ms on CPU with our decoder written in C ๐Ÿš€ #### ๐Ÿ”ฅ **Fixed-point decoder**: Fixed-point arithmetic at the decoder for bit-exact results on different hardwares ๐Ÿ”ฅ #### ๐Ÿ–ผ๏ธ **I/O format**: Encode PNG, PPM and YUV 420 & 444 files with a bitdepth of 8 to 16 bits ๐Ÿ–ผ๏ธ
#
### Latest release: ๐ŸŽ‰ __Cool-chic 3.4: 30% less complex!__ ๐ŸŽ‰
- New and improved latent **upsampling module** - Leverage symmetric and separable convolution kernels to reduce complexity & parameters count - Learn two filters per upsampling step instead of one for all upsampling steps - 1% to 5% **rate reduction** for the same image quality - **30% complexity reduction** using a smaller Auto-Regressive Module - From 2000 MAC / decoded pixel to 1300 MAC / decoded pixel - **10% faster** decoding speed Check-out the [release history](https://github.com/Orange-OpenSource/Cool-Chic/releases) to see previous versions of Cool-chic. # Setup More details are available on the [Cool-chic page](https://orange-opensource.github.io/Cool-Chic/getting_started/quickstart.html) ```bash # We need to get these packages to compile the C API and bind it to python. sudo add-apt-repository -y ppa:deadsnakes/ppa && sudo apt update sudo apt install -y build-essential python3.10-dev pip git clone https://github.com/Orange-OpenSource/Cool-Chic.git && cd Cool-Chic # Install create and activate virtual env python3.10 -m pip install virtualenv python3.10 -m virtualenv venv && source venv/bin/activate # Install Cool-chic pip install -e . # Sanity check python -m test.sanity_check ``` You're good to go! ## Performance The Cool-chic page provides [comprehensive rate-distortion results and compressed bitstreams](https://orange-opensource.github.io/Cool-Chic/getting_started/results.html) allowing to reproduce the results inside the ```results/``` directory.
BD-rate of Cool-chic 3.4 vs. [%] Avg. decoder complexity
Cheng ELIC Cool-chic 3.3 C3 HEVC (HM 16) VVC (VTM 19) MAC / pixel CPU Time [ms]
kodak -4.2 % +7.5 % -0.9 % -4.3 % -17.2 % +3.4 % 1303 74
clic20-pro-valid -13.2 % -0.2 % -0.3 % -1.3 % -25.1 % -2.3 %
1357 354
jvet / / -0.2 % / -18.3 % +18.6 % 1249 143

_Decoding time are obtained on a single CPU core of an an AMD EPYC 7282 16-Core Processor_ _PSNR is computed in the RGB domain for kodak and CLIC20, in the YUV420 domain for jvet_ ### Kodak
Kodak rd results

### CLIC20 Pro Valid
CLIC20 rd results

### JVET Class B
JVET class B rd results


# Thanks 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.](https://arxiv.org/abs/2312.02753) [contributors-shield]: https://img.shields.io/github/contributors/Orange-OpenSource/Cool-Chic.svg?style=for-the-badge [contributors-url]: https://github.com/Orange-OpenSource/Cool-Chic/graphs/contributors [forks-shield]: https://img.shields.io/github/forks/Orange-OpenSource/Cool-Chic.svg?style=for-the-badge [forks-url]: https://github.com/Orange-OpenSource/Cool-Chic/network/members [stars-shield]: https://img.shields.io/github/stars/Orange-OpenSource/Cool-Chic.svg?style=for-the-badge [stars-url]: https://github.com/Orange-OpenSource/Cool-Chic/stargazers [issues-shield]: https://img.shields.io/github/issues/Orange-OpenSource/Cool-Chic.svg?style=for-the-badge [issues-url]: https://github.com/Orange-OpenSource/Cool-Chic/issues [license-shield]: https://img.shields.io/github/license/Orange-OpenSource/Cool-Chic.svg?style=for-the-badge [license-url]: https://github.com/Orange-OpenSource/Cool-Chic/blob/master/LICENSE.txt [pytorch-shield]: https://img.shields.io/badge/PyTorch-0769AD?style=for-the-badge&logo=pytorch&logoColor=white [pytorch-url]: https://pytorch.org/
#
Cool-chic Logo