{"ID":2823933,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.24035","arxiv_id":"2512.24035","title":"Reinforced Diffusion: Learning to Push the Limits of Anisotropic Diffusion for Image Denoising","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.24035","url_pdf":"https://arxiv.org/pdf/2512.24035v1","authors":"[\"Xinran Qin\",\"Yuhui Quan\",\"Ruotao Xu\",\"Hui Ji\"]","published":"2025-12-30T07:23:15Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Reinforcement Learning\",\"Diffusion Model\",\"Convolutional Neural Network\"]","has_code":false}