# On the Importance of Denoising when Learning to Compress Images

arXiv: https://arxiv.org/abs/2307.06233 · HTML: https://mlsanity.com/paper/2307.06233/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 12 Jul 2023.

## Builds on (most cited first, 11 of 11)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Efficient Nonlinear Transforms for Lossy Image Compression](https://mlsanity.com/paper/1802.00847/) (2018)
- [Natural Image Noise Dataset](https://mlsanity.com/paper/1906.00270/) (2019)
- [Toward Interactive Modulation for Photo-Realistic Image Restoration](https://mlsanity.com/paper/2105.03085/) (2021)
- [End-to-end optimized image compression with competition of prior distributions](https://mlsanity.com/paper/2111.09172/) (2021)

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

- [All-in-One Image Compression and Restoration](https://mlsanity.com/paper/2502.03649/) (2025)
- [DeCompress: Denoising via Neural Compression](https://mlsanity.com/paper/2503.22015/) (2025)
- [Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework](https://mlsanity.com/paper/2506.12693/) (2025)
- [FLLIC: Functionally Lossless Image Compression](https://mlsanity.com/paper/2401.13616/) (2024)
- [Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset](https://mlsanity.com/paper/2501.08924/) (2025)

## Abstract (arXiv)

Image noise is ubiquitous in photography. However, image noise is not compressible nor desirable, thus attempting to convey the noise in compressed image bitstreams yields sub-par results in both rate and distortion. We propose to explicitly learn the image denoising task when training a codec. Therefore, we leverage the Natural Image Noise Dataset, which offers a wide variety of scenes captured with various ISO numbers, leading to different noise levels, including insignificant ones. Given this training set, we supervise the codec with noisy-clean image pairs, and show that a single model trained based on a mixture of images with variable noise levels appears to yield best-in-class results with both noisy and clean images, achieving better rate-distortion than a compression-only model or even than a pair of denoising-then-compression models with almost one order of magnitude fewer GMac operations.