# Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments

arXiv: https://arxiv.org/abs/2012.05116 · HTML: https://mlsanity.com/paper/2012.05116/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [Zero-Reference Low-Light Enhancement via Physical Quadruple Priors](https://mlsanity.com/paper/2403.12933/) (2024)
- [Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution](https://mlsanity.com/paper/2207.01797/) (2022)
- [LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond](https://mlsanity.com/paper/2410.09831/) (2024)
- [Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation](https://mlsanity.com/paper/2501.00637/) (2024)
- [Modular Degradation Simulation and Restoration for Under-Display Camera](https://mlsanity.com/paper/2209.11455/) (2022)
- [Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation](https://mlsanity.com/paper/2210.03792/) (2022)
- [Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats](https://mlsanity.com/paper/2410.02764/) (2024)
- [Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark](https://mlsanity.com/paper/2607.29684/) (2026)
- [Reinforcement Learning of Self Enhancing Camera Image and Signal Processing](https://mlsanity.com/paper/2111.07499/) (2021)
- [Seeing Far in the Dark with Patterned Flash](https://mlsanity.com/paper/2207.12570/) (2022)
- [Multiple Latent Space Mapping for Compressed Dark Image Enhancement](https://mlsanity.com/paper/2403.07622/) (2024)
- [Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery](https://mlsanity.com/paper/2511.16887/) (2025)

## Abstract (arXiv)

We introduce a neural network-based method to denoise pairs of images taken in quick succession, with and without a flash, in low-light environments. Our goal is to produce a high-quality rendering of the scene that preserves the color and mood from the ambient illumination of the noisy no-flash image, while recovering surface texture and detail revealed by the flash. Our network outputs a gain map and a field of kernels, the latter obtained by linearly mixing elements of a per-image low-rank kernel basis. We first apply the kernel field to the no-flash image, and then multiply the result with the gain map to create the final output. We show our network effectively learns to produce high-quality images by combining a smoothed out estimate of the scene's ambient appearance from the no-flash image, with high-frequency albedo details extracted from the flash input. Our experiments show significant improvements over alternative captures without a flash, and baseline denoisers that use flash no-flash pairs. In particular, our method produces images that are both noise-free and contain accurate ambient colors without the sharp shadows or strong specular highlights visible in the flash image.