Saved in:
Bibliographic Details
Main Authors: Qin, Xinran, Quan, Yuhui, Xu, Ruotao, Ji, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.24035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914226967150592
author Qin, Xinran
Quan, Yuhui
Xu, Ruotao
Ji, Hui
author_facet Qin, Xinran
Quan, Yuhui
Xu, Ruotao
Ji, Hui
contents Image denoising is an important problem in low-level vision and serves as a critical module for many image recovery tasks. Anisotropic diffusion is a wide family of image denoising approaches with promising performance. However, traditional anisotropic diffusion approaches use explicit diffusion operators which are not well adapted to complex image structures. As a result, their performance is limited compared to recent learning-based approaches. In this work, we describe a trainable anisotropic diffusion framework based on reinforcement learning. By modeling the denoising process as a series of naive diffusion actions with order learned by deep Q-learning, we propose an effective diffusion-based image denoiser. The diffusion actions selected by deep Q-learning at different iterations indeed composite a stochastic anisotropic diffusion process with strong adaptivity to different image structures, which enjoys improvement over the traditional ones. The proposed denoiser is applied to removing three types of often-seen noise. The experiments show that it outperforms existing diffusion-based methods and competes with the representative deep CNN-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24035
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reinforced Diffusion: Learning to Push the Limits of Anisotropic Diffusion for Image Denoising
Qin, Xinran
Quan, Yuhui
Xu, Ruotao
Ji, Hui
Computer Vision and Pattern Recognition
Image denoising is an important problem in low-level vision and serves as a critical module for many image recovery tasks. Anisotropic diffusion is a wide family of image denoising approaches with promising performance. However, traditional anisotropic diffusion approaches use explicit diffusion operators which are not well adapted to complex image structures. As a result, their performance is limited compared to recent learning-based approaches. In this work, we describe a trainable anisotropic diffusion framework based on reinforcement learning. By modeling the denoising process as a series of naive diffusion actions with order learned by deep Q-learning, we propose an effective diffusion-based image denoiser. The diffusion actions selected by deep Q-learning at different iterations indeed composite a stochastic anisotropic diffusion process with strong adaptivity to different image structures, which enjoys improvement over the traditional ones. The proposed denoiser is applied to removing three types of often-seen noise. The experiments show that it outperforms existing diffusion-based methods and competes with the representative deep CNN-based methods.
title Reinforced Diffusion: Learning to Push the Limits of Anisotropic Diffusion for Image Denoising
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.24035