We propose a lightweight learned video codec with 900 multiplications per decoded pixel and 800 parameters overall. To the best of our knowledge, this is one of the neural video codecs with the lowest decoding complexity. It is built upon the overfitted image codec Cool-chic and supplements it with an inter coding module to leverage the video's temporal redundancies. The proposed model is able to compress videos using both low-delay and random access configurations and achieves rate-distortion close to AVC while out-performing other overfitted codecs such as FFNeRV. The system is made open-source: orange-opensource.github.io/Cool-Chic.
@article{arxiv.2402.03179,
title = {Cool-chic video: Learned video coding with 800 parameters},
author = {Thomas Leguay and Théo Ladune and Pierrick Philippe and Olivier Déforges},
journal= {arXiv preprint arXiv:2402.03179},
year = {2025}
}
Comments
10 pages, published in Data Compression Conference 2024