# Rethinking Noise Synthesis and Modeling in Raw Denoising

arXiv: https://arxiv.org/abs/2110.04756 · HTML: https://mlsanity.com/paper/2110.04756/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 10 Oct 2021.

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

- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [Burst Denoising with Kernel Prediction Networks](https://mlsanity.com/paper/1712.02327/) (2017)
- [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)
- [Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation](https://mlsanity.com/paper/2007.05946/) (2020)
- [GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling](https://mlsanity.com/paper/1905.11172/) (2019)
- [Learning Camera-Aware Noise Models](https://mlsanity.com/paper/2008.09370/) (2020)
- [High-level numerical simulations of noise in CCD and CMOS photosensors: review and tutorial](https://mlsanity.com/paper/1412.4031/) (2014)

## Built on by (most cited first, 30 of 62)

- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [Realistic Blur Synthesis for Learning Image Deblurring](https://mlsanity.com/paper/2202.08771/) (2022)
- [Dancing under the stars: video denoising in starlight](https://mlsanity.com/paper/2204.04210/) (2022)
- [IDR: Self-Supervised Image Denoising via Iterative Data Refinement](https://mlsanity.com/paper/2111.14358/) (2021)
- [KBNet: Kernel Basis Network for Image Restoration](https://mlsanity.com/paper/2303.02881/) (2023)
- [Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising](https://mlsanity.com/paper/2303.14934/) (2023)
- [ExposureDiffusion: Learning to Expose for Low-light Image Enhancement](https://mlsanity.com/paper/2307.07710/) (2023)
- [Modeling sRGB Camera Noise with Normalizing Flows](https://mlsanity.com/paper/2206.00812/) (2022)
- [Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling](https://mlsanity.com/paper/2207.06103/) (2022)
- [A Unified Conditional Framework for Diffusion-based Image Restoration](https://mlsanity.com/paper/2305.20049/) (2023)
- [Towards General Low-Light Raw Noise Synthesis and Modeling](https://mlsanity.com/paper/2307.16508/) (2023)
- [Raw Image Reconstruction with Learned Compact Metadata](https://mlsanity.com/paper/2302.12995/) (2023)
- [Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images](https://mlsanity.com/paper/2206.01103/) (2022)
- [Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network](https://mlsanity.com/paper/2205.04721/) (2022)
- [Estimating Fine-Grained Noise Model via Contrastive Learning](https://mlsanity.com/paper/2204.01716/) (2022)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Learning to See in the Extremely Dark](https://mlsanity.com/paper/2506.21132/) (2025)
- [Learning Physics-Informed Noise Models from Dark Frames for Low-Light Raw Image Denoising](https://mlsanity.com/paper/2310.09126/) (2023)
- [Time-Aware Auto White Balance in Mobile Photography](https://mlsanity.com/paper/2504.05623/) (2025)
- [Beyond Learned Metadata-based Raw Image Reconstruction](https://mlsanity.com/paper/2306.12058/) (2023)
- [CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring](https://mlsanity.com/paper/2408.14930/) (2024)
- [RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset](https://mlsanity.com/paper/2305.00767/) (2023)
- [Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging](https://mlsanity.com/paper/2601.23276/) (2026)
- [Modular Degradation Simulation and Restoration for Under-Display Camera](https://mlsanity.com/paper/2209.11455/) (2022)
- [Visibility Constrained Wide-band Illumination Spectrum Design for Seeing-in-the-Dark](https://mlsanity.com/paper/2303.11642/) (2023)
- [Toward Efficient Deep Blind RAW Image Restoration](https://mlsanity.com/paper/2409.18204/) (2024)
- [Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement](https://mlsanity.com/paper/2409.07040/) (2024)
- [Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers](https://mlsanity.com/paper/2409.11256/) (2024)
- [Recurrent Spike-based Image Restoration under General Illumination](https://mlsanity.com/paper/2308.03018/) (2023)
- [Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection](https://mlsanity.com/paper/2509.09183/) (2025)

## Abstract (arXiv)

The lack of large-scale real raw image denoising dataset gives rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors. Existing methods are unable to model all noise sources accurately, and building a noise model for each sensor is also laborious. In this paper, we introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors. Two efficient and generic techniques: pattern-aligned patch sampling and high-bit reconstruction help accurate synthesis of spatial-correlated noise and high-bit noise respectively. We conduct systematic experiments on SIDD and ELD datasets. The results show that (1) our method outperforms existing methods and demonstrates wide generalization on different sensors and lighting conditions. (2) Recent conclusions derived from DNN-based noise modeling methods are actually based on inaccurate noise parameters. The DNN-based methods still cannot outperform physics-based statistical methods.