# Low-complexity Overfitted Neural Image Codec

arXiv: https://arxiv.org/abs/2307.12706 · HTML: https://mlsanity.com/paper/2307.12706/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2023.

## Built on by (most cited first, 13 of 13)

- [GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting](https://mlsanity.com/paper/2403.08551/) (2024)
- [C3: High-performance and low-complexity neural compression from a single image or video](https://mlsanity.com/paper/2312.02753/) (2023)
- [Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion](https://mlsanity.com/paper/2412.00505/) (2024)
- [Cool-chic video: Learned video coding with 800 parameters](https://mlsanity.com/paper/2402.03179/) (2024)
- [Content-Aware Mamba for Learned Image Compression](https://mlsanity.com/paper/2508.02192/) (2025)
- [An Efficient Implicit Neural Representation Image Codec Based on Mixed Autoregressive Model for Low-Complexity Decoding](https://mlsanity.com/paper/2401.12587/) (2024)
- [Quantum Implicit Neural Compression](https://mlsanity.com/paper/2412.19828/) (2024)
- [Compact Latent Representation for Image Compression (CLRIC)](https://mlsanity.com/paper/2502.14937/) (2025)
- [Goal-Oriented Source Coding using LDPC Codes for Compressed-Domain Image Classification](https://mlsanity.com/paper/2503.11954/) (2025)
- [LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transforms](https://mlsanity.com/paper/2504.21778/) (2025)
- [From Noise to Latent: Generating Gaussian Latents for INR-Based Image Compression](https://mlsanity.com/paper/2511.08009/) (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)

We propose a neural image codec at reduced complexity which overfits the decoder parameters to each input image. While autoencoders perform up to a million multiplications per decoded pixel, the proposed approach only requires 2300 multiplications per pixel. Albeit low-complexity, the method rivals autoencoder performance and surpasses HEVC performance under various coding conditions. Additional lightweight modules and an improved training process provide a 14% rate reduction with respect to previous overfitted codecs, while offering a similar complexity. This work is made open-source at https://orange-opensource.github.io/Cool-Chic/