# DiffuseRAW: End-to-End Generative RAW Image Processing for Low-Light Images arXiv: https://arxiv.org/abs/2402.18575 ยท HTML: https://mlsanity.com/paper/2402.18575/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. - Builds on 38 of its 83 references that are in the map. - First posted on arXiv 13 Dec 2023. ## Placed in - Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/) ## Builds on (most cited first, 30 of 38) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022) - [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022) - [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022) - [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021) - [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021) - [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016) - [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018) - [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022) - [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020) - [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018) - [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019) - [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018) - [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022) - [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020) - [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015) - [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015) - [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021) - [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022) - [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020) - [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019) - [EpiGRAF: Rethinking training of 3D GANs](https://mlsanity.com/paper/2206.10535/) (2022) - [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018) - [Rethinking Noise Synthesis and Modeling in Raw Denoising](https://mlsanity.com/paper/2110.04756/) (2021) - [ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2105.10697/) (2021) - [Dancing under the stars: video denoising in starlight](https://mlsanity.com/paper/2204.04210/) (2022) - [WESPE: Weakly Supervised Photo Enhancer for Digital Cameras](https://mlsanity.com/paper/1709.01118/) (2017) - [Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling](https://mlsanity.com/paper/2207.06103/) (2022) ## Built on by (most cited first, 4 of 4) - [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024) - [Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection](https://mlsanity.com/paper/2509.09183/) (2025) - [Beyond the Visible: Jointly Attending to Spectral and Spatial Dimensions with HSI-Diffusion for the FINCH Spacecraft](https://mlsanity.com/paper/2406.10724/) (2024) - [EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion](https://mlsanity.com/paper/2607.06217/) (2026) ## Abstract (arXiv) Imaging under extremely low-light conditions presents a significant challenge and is an ill-posed problem due to the low signal-to-noise ratio (SNR) caused by minimal photon capture. Previously, diffusion models have been used for multiple kinds of generative tasks and image-to-image tasks, however, these models work as a post-processing step. These diffusion models are trained on processed images and learn on processed images. However, such approaches are often not well-suited for extremely low-light tasks. Unlike the task of low-light image enhancement or image-to-image enhancement, we tackle the task of learning the entire image-processing pipeline, from the RAW image to a processed image. For this task, a traditional image processing pipeline often consists of multiple specialized parts that are overly reliant on the downstream tasks. Unlike these, we develop a new generative ISP that relies on fine-tuning latent diffusion models on RAW images and generating processed long-exposure images which allows for the apt use of the priors from large text-to-image generation models. We evaluate our approach on popular end-to-end low-light datasets for which we see promising results and set a new SoTA on the See-in-Dark (SID) dataset. Furthermore, with this work, we hope to pave the way for more generative and diffusion-based image processing and other problems on RAW data.