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

Théo Ladune, Pierrick Philippe, Félix Henry, Gordon Clare, Thomas Leguay

ICCV 2023 pp. 13515-13522

doi:10.1109/ICCV51070.2023.01243 /iccv/2023/ladune2023iccv-coolchic/

Abstract

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 performance close to modern conventional MPEG codecs such as HEVC and is competitive with popular autoencoder-based systems. This method is inspired by Coordinate-based Neural Representations, where an image is represented as a learned function which maps pixel coordinates to RGB values. The parameters of the mapping function are then sent using entropy coding. At the receiver side, the compressed image is obtained by evaluating the mapping function for all pixel coordinates. COOL-CHIC implementation is made open-source.

PDF ICCV Semantic Scholar

Cite

Text

Ladune et al. "COOL-CHIC: Coordinate-Based Low Complexity Hierarchical Image Codec." International Conference on Computer Vision, 2023. doi:10.1109/ICCV51070.2023.01243

Markdown

[Ladune et al. "COOL-CHIC: Coordinate-Based Low Complexity Hierarchical Image Codec." International Conference on Computer Vision, 2023.](https://mlanthology.org/iccv/2023/ladune2023iccv-coolchic/) doi:10.1109/ICCV51070.2023.01243

BibTeX

@inproceedings{ladune2023iccv-coolchic,
  title     = {{COOL-CHIC: Coordinate-Based Low Complexity Hierarchical Image Codec}},
  author    = {Ladune, Théo and Philippe, Pierrick and Henry, Félix and Clare, Gordon and Leguay, Thomas},
  booktitle = {International Conference on Computer Vision},
  year      = {2023},
  pages     = {13515-13522},
  doi       = {10.1109/ICCV51070.2023.01243},
  url       = {https://mlanthology.org/iccv/2023/ladune2023iccv-coolchic/}
}