# Exploring Inter-frequency Guidance of Image for Lightweight Gaussian Denoising

arXiv: https://arxiv.org/abs/2112.11779 · HTML: https://mlsanity.com/paper/2112.11779/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 22 Dec 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration](https://mlsanity.com/paper/1508.02848/) (2015)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Residual Dense Network for Image Restoration](https://mlsanity.com/paper/1812.10477/) (2018)
- [Learning Dual Convolutional Neural Networks for Low-Level Vision](https://mlsanity.com/paper/1805.05020/) (2018)
- [Hartley Spectral Pooling for Deep Learning](https://mlsanity.com/paper/1810.04028/) (2018)

## Built on by (most cited first, 1 of 1)

- [Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training](https://mlsanity.com/paper/2304.01805/) (2023)

## Abstract (arXiv)

Image denoising is of vital importance in many imaging or computer vision related areas. With the convolutional neural networks showing strong capability in computer vision tasks, the performance of image denoising has also been brought up by CNN based methods. Though CNN based image denoisers show promising results on this task, most of the current CNN based methods try to learn the mapping from noisy image to clean image directly, which lacks the explicit exploration of prior knowledge of images and noises. Natural images are observed to obey the reciprocal power law, implying the low-frequency band of image tend to occupy most of the energy. Thus in the condition of AGWN (additive gaussian white noise) deterioration, low-frequency band tend to preserve a higher PSNR than high-frequency band. Considering the spatial morphological consistency of different frequency bands, low-frequency band with more fidelity can be used as a guidance to refine the more contaminated high-frequency bands. Based on this thought, we proposed a novel network architecture denoted as IGNet, in order to refine the frequency bands from low to high in a progressive manner. Firstly, it decomposes the feature maps into high- and low-frequency subbands using DWT (discrete wavelet transform) iteratively, and then each low band features are used to refine the high band features. Finally, the refined feature maps are processed by a decoder to recover the clean result. With this design, more inter-frequency prior and information are utilized, thus the model size can be lightened while still perserves competitive results. Experiments on several public datasets show that our model obtains competitive performance comparing with other state-of-the-art methods yet with a lightweight structure.