# Overfitted image coding at reduced complexity

arXiv: https://arxiv.org/abs/2403.11651 · HTML: https://mlsanity.com/paper/2403.11651/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2024.

## Built on by (most cited first, 5 of 5)

- [Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion](https://mlsanity.com/paper/2412.00505/) (2024)
- [Compact Latent Representation for Image Compression (CLRIC)](https://mlsanity.com/paper/2502.14937/) (2025)
- [LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transforms](https://mlsanity.com/paper/2504.21778/) (2025)
- [TreeNet: A Light Weight Model for Low Bitrate Image Compression](https://mlsanity.com/paper/2512.16743/) (2025)
- [PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding](https://mlsanity.com/paper/2609.09020/) (2026)

## Abstract (arXiv)

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 performance on par with VVC while requiring around 2000 multiplications per decoded pixel. This paper proposes to decrease Cool-chic encoding and decoding complexity. The encoding complexity is reduced by shortening Cool-chic training, up to the point where no overfitting is performed at all. It is also shown that a tiny neural decoder with 300 multiplications per pixel still outperforms HEVC. A near real-time CPU implementation of this decoder is made available at https://orange-opensource.github.io/Cool-Chic/.