# Fast, Trainable, Multiscale Denoising

arXiv: https://arxiv.org/abs/1802.06130 · HTML: https://mlsanity.com/paper/1802.06130/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2018.

## Built on by (most cited first, 2 of 2)

- [Solving Image PDEs with a Shallow Network](https://mlsanity.com/paper/2110.08327/) (2021)
- [A Dictionary Based Approach for Removing Out-of-Focus Blur](https://mlsanity.com/paper/2406.11330/) (2024)

## Abstract (arXiv)

Denoising is a fundamental imaging problem. Versatile but fast filtering has been demanded for mobile camera systems. We present an approach to multiscale filtering which allows real-time applications on low-powered devices. The key idea is to learn a set of kernels that upscales, filters, and blends patches of different scales guided by local structure analysis. This approach is trainable so that learned filters are capable of treating diverse noise patterns and artifacts. Experimental results show that the presented approach produces comparable results to state-of-the-art algorithms while processing time is orders of magnitude faster.