# Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising

arXiv: https://arxiv.org/abs/1806.05229 · HTML: https://mlsanity.com/paper/1806.05229/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2018.

## Built on by (most cited first, 16 of 16)

- [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)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [Accurate Image Restoration with Attention Retractable Transformer](https://mlsanity.com/paper/2210.01427/) (2022)
- [Improving Image Restoration by Revisiting Global Information Aggregation](https://mlsanity.com/paper/2112.04491/) (2021)
- [C2N: Practical Generative Noise Modeling for Real-World Denoising](https://mlsanity.com/paper/2202.09533/) (2022)
- [Improving Image Restoration through Removing Degradations in Textual Representations](https://mlsanity.com/paper/2312.17334/) (2023)
- [KBNet: Kernel Basis Network for Image Restoration](https://mlsanity.com/paper/2303.02881/) (2023)
- [COLA-Net: Collaborative Attention Network for Image Restoration](https://mlsanity.com/paper/2103.05961/) (2021)
- [Restoration by Generation with Constrained Priors](https://mlsanity.com/paper/2312.17161/) (2023)
- [Masked Autoencoders as Image Processors](https://mlsanity.com/paper/2303.17316/) (2023)
- [Fast and High-Quality Image Denoising via Malleable Convolutions](https://mlsanity.com/paper/2201.00392/) (2022)
- [A cross Transformer for image denoising](https://mlsanity.com/paper/2310.10408/) (2023)
- [Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond](https://mlsanity.com/paper/2201.10084/) (2022)
- [Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing](https://mlsanity.com/paper/2504.13975/) (2025)
- [Enhancing Low-resolution Image Representation Through Normalizing Flows](https://mlsanity.com/paper/2601.06834/) (2026)

## Abstract (arXiv)

Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for modern methods that leverage deep neural networks trained to regress to clean images from noisy inputs. One recourse is to rely on "internal" image statistics, by searching for similar patterns within the input image itself. In this work, we propose a new method for natural image denoising that trains a deep neural network to determine whether patches in a noisy image input share common underlying patterns. Given a pair of noisy patches, our network predicts whether different sub-band coefficients of the original noise-free patches are similar. The denoising algorithm then aggregates matched coefficients to obtain an initial estimate of the clean image. Finally, this estimate is provided as input, along with the original noisy image, to a standard regression-based denoising network. Experiments show that our method achieves state-of-the-art color image denoising performance, including with a blind version that trains a common model for a range of noise levels, and does not require knowledge of level of noise in an input image. Our approach also has a distinct advantage when training with limited amounts of training data.