paper-with-me

Papers

Cool-chic video: Learned video coding with 800 parameters

2024-02-05 · Thomas Leguay, Théo Ladune, Pierrick Philippe, Olivier Déforges

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.

📄 PDF Abstract BibTeX arXiv:2402.03179

Code (1)

orange-opensource/cool-chic 공식 구현 pytorch

Similar Papers 제목 키워드 기반

COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec

2022-12-11 · ICCV 2023 1 · Théo Ladune, Pierrick Philippe, Félix Henry, Gordon Clare 외

We introduce COOL-CHIC, a Coordinate-based Low Complexity Hierarchical Image Codec. It is a learned alternative to autoencoders with 629 parameters and 680 multiplications per decoded pixel. COOL-CHIC offers compression …

C3: High-performance and low-complexity neural compression from a single image or video

2023-12-05 · CVPR 2024 1 · Hyunjik Kim, Matthias Bauer, Lucas Theis, Jonathan Richard Schwarz 외

Most neural compression models are trained on large datasets of images or videos in order to generalize to unseen data. Such generalization typically requires large and expressive architectures with a high decoding compl…

Video Compression

Cool-Chic: Perceptually Tuned Low Complexity Overfitted Image Coder

2024-01-04 · Théo Ladune, Pierrick Philippe, Gordon Clare, Félix Henry 외

This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight ima…

Image Compression

Improved Encoding for Overfitted Video Codecs

2025-01-28 · Thomas Leguay, Théo Ladune, Pierrick Philippe, Olivier Deforges

Overfitted neural video codecs offer a decoding complexity orders of magnitude smaller than their autoencoder counterparts. Yet, this low complexity comes at the cost of limited compression efficiency, in part due to the…

Optical Flow Estimation

Overfitted image coding at reduced complexity

2024-03-18 · Théophile Blard, Théo Ladune, Pierrick Philippe, Gordon Clare 외

Overfitted image codecs offer compelling compression performance and low decoder complexity, through the overfitting of a lightweight decoder for each image. Such codecs include Cool-chic, which presents image coding per…

CPUDecoderImage Compression