# Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising

arXiv: https://arxiv.org/abs/2505.00045 · HTML: https://mlsanity.com/paper/2505.00045/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2025.

## Built on by (most cited first, 9 of 9)

- [Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging](https://mlsanity.com/paper/2601.23276/) (2026)
- [AIM 2025 Challenge on Real-World RAW Image Denoising](https://mlsanity.com/paper/2510.06601/) (2025)
- [Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising](https://mlsanity.com/paper/2607.11090/) (2026)
- [Physics-Guided Rectified Flow for Low-light RAW Image Enhancement](https://mlsanity.com/paper/2509.08330/) (2025)
- [Hybrid Event Frame Sensors: Modeling, Calibration, and Simulation](https://mlsanity.com/paper/2511.18037/) (2025)
- [GuidNoise: Single-Pair Guided Diffusion for Generalized Noise Synthesis](https://mlsanity.com/paper/2512.04456/) (2025)
- [A Physically-Grounded Attack and Adaptive Defense Framework for Real-World Low-Light Image Enhancement](https://mlsanity.com/paper/2603.14304/) (2026)
- [NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness](https://mlsanity.com/paper/2603.20005/) (2026)
- [Practical Noise Modeling for SPAD Intensity Imaging](https://mlsanity.com/paper/2608.00489/) (2026)

## Abstract (arXiv)

Noise synthesis is a promising solution for addressing the data shortage problem in data-driven low-light RAW image denoising. However, accurate noise synthesis methods often necessitate labor-intensive calibration and profiling procedures during preparation, preventing them from landing to practice at scale. This work introduces a practically simple noise synthesis pipeline based on detailed analyses of noise properties and extensive justification of widespread techniques. Compared to other approaches, our proposed pipeline eliminates the cumbersome system gain calibration and signal-independent noise profiling steps, reducing the preparation time for noise synthesis from days to hours. Meanwhile, our method exhibits strong denoising performance, showing an up to 0.54dB PSNR improvement over the current state-of-the-art noise synthesis technique. Code is released at https://github.com/SonyResearch/raw_image_denoising