Explore the docs »

What's new in 3.4.1? · Decode some bitstreams · Coding performance

Cool-chic (pronounced /kul ʃik/ as in French 🥖🧀🍷) is a low-complexity neural image codec based on overfitting.

• 🏆 Coding performance: Cool-chic compresses images as well as H.266/VVC

• 🪶 Lightweight decoder: Cool-chic decoder performs only 1000 multiplications per decoded pixel

• 🚀 Fast CPU-only decoder: Decode a 1280x720 image in 100 ms on CPU with our decoder written in C

• 🖼️ I/O format: Encode PNG, PPM and YUV 420 & 444 files with a bitdepth of 8 to 16 bits

Happy new year release: 🎉 Cool-chic 3.4.1: Faster encoder! 🎉

• Speed-up GPU Encoding up to 3 times! Check-out the detailed encoding speed-up measurements
• Change encoder configuration files with better medium and slow encoding presets

Check-out the release history to see previous versions of Cool-chic.

Setup

More details are available on the Cool-chic page

# 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!

Compression performance

The Cool-chic page provides comprehensive rate-distortion results and compressed bitstreams](https://orange-opensource.github.io/Cool-Chic/results/image/reproduce_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 (BCDEF)	/	/	-0.2 %	/	-18.3 %	+18.6 %	1249	143
jvet (class B)	/	/	+0.9%	/	-9.9 %	+20.7 %	1300	282
jvet (class C)	/	/	-1.3%	/	-16.1 %	+9.2 %	1289	69
jvet (class D)	/	/	-1.4%	/	-12.4 %	+9.6 %	948	18
jvet (class E)	/	/	-3.8%	/	-6.2 %	+27.8 %	1347	125
jvet (class F)	/	/	+0.2%	/	-31.8 %	+20.6 %	1249	182

Compression performance and decoding time

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

CLIC20 Pro Valid

JVET Class B

Encoding time

The graphs below present the time required to encode several images resolutions on different hardwares. These figures are obtained using the cfg/enc/medium_30k.cfg encoding configuration.

Kodak image 512x768

CLIC20 Pro Valid image 1363x2048

JVET Class E image 720x1280

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.