Learning filter selection policies for interpretable image denoising in parametrised action space
Authors:
Open Access
- 27 November 2023
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 18 (4) , 951-960
Abstract
The denoising of images is an important research direction in computer vision. We consider the image denoising task as an estimation problem of the filtering policy related to image features, which is different from end‐to‐end image mapping. Commonly used simple filters such as gaussian filtering and bilateral filtering have fixed global denoising policies. However, the denoising policies of different filters can only adapt to limited image features. To solve this problem, we propose a method that applies different filters to different spatial ranges and adjusts the parameters of these filters simultaneously. Since not all filters can be easily transformed into differentiable forms and it is difficult to obtain paired datasets of filter action areas, we use reinforcement learning (RL) methods to estimate the spatial domain action range and adjustable parameters of filters, respectively. Furthermore, for removing higher intensity noise, simple filters can iteratively approximate higher‐order denoising policies and obtain more accurate and stable denoising results with the increase of iteration steps. Experimental results show that our proposed method can not only generate intuitive and interpretable denoising policies but also achieve comparable or better visual effects and computational efficiency than baseline methods.Keywords
This publication has 25 references indexed in Scilit:
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image RestorationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- External Patch Prior Guided Internal Clustering for Image Denoising2015
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising2015
- Structured Overcomplete Sparsifying Transform Learning with Convergence Guarantees and ApplicationsInternational Journal of Computer Vision, 2014
- Weighted Nuclear Norm Minimization with Application to Image Denoising2014
- Texture Enhanced Image Denoising via Gradient Histogram Preservation2013
- Nonlocally Centralized Sparse Representation for Image RestorationIEEE Transactions on Image Processing, 2012
- From learning models of natural image patches to whole image restoration2011
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007