# SUMD: Super U-shaped Matrix Decomposition Convolutional neural network for Image denoising

arXiv: https://arxiv.org/abs/2204.04861 · HTML: https://mlsanity.com/paper/2204.04861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Variational Denoising Network: Toward Blind Noise Modeling and Removal](https://mlsanity.com/paper/1908.11314/) (2019)
- [NBNet: Noise Basis Learning for Image Denoising with Subspace Projection](https://mlsanity.com/paper/2012.15028/) (2020)
- [Is Attention Better Than Matrix Decomposition?](https://mlsanity.com/paper/2109.04553/) (2021)

## Abstract (arXiv)

In this paper, we propose a novel and efficient CNN-based framework that leverages local and global context information for image denoising. Due to the limitations of convolution itself, the CNN-based method is generally unable to construct an effective and structured global feature representation, usually called the long-distance dependencies in the Transformer-based method. To tackle this problem, we introduce the matrix decomposition module(MD) in the network to establish the global context feature, comparable to the Transformer based method performance. Inspired by the design of multi-stage progressive restoration of U-shaped architecture, we further integrate the MD module into the multi-branches to acquire the relative global feature representation of the patch range at the current stage. Then, the stage input gradually rises to the overall scope and continuously improves the final feature. Experimental results on various image denoising datasets: SIDD, DND, and synthetic Gaussian noise datasets show that our model(SUMD) can produce comparable visual quality and accuracy results with Transformer-based methods.