{"ID":2842065,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09965","arxiv_id":"2511.09965","title":"Equivariant Sampling for Improving Diffusion Model-based Image Restoration","abstract":"Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this paper, we address the limitations of current problem-agnostic DMIR methods by analyzing their sampling process and providing effective solutions. We introduce EquS, a DMIR method that imposes equivariant information through dual sampling trajectories. To further boost EquS, we propose the Timestep-Aware Schedule (TAS) and introduce EquS$^+$. TAS prioritizes deterministic steps to enhance certainty and sampling efficiency. Extensive experiments on benchmarks demonstrate that our method is compatible with previous problem-agnostic DMIR methods and significantly boosts their performance without increasing computational costs. Our code is available at https://github.com/FouierL/EquS.","short_abstract":"Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this...","url_abs":"https://arxiv.org/abs/2511.09965","url_pdf":"https://arxiv.org/pdf/2511.09965v1","authors":"[\"Chenxu Wu\",\"Qingpeng Kong\",\"Peiang Zhao\",\"Wendi Yang\",\"Wenxin Ma\",\"Fenghe Tang\",\"Zihang Jiang\",\"S. Kevin Zhou\"]","published":"2025-11-13T04:56:53Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":607096,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2842065,"paper_url":"https://arxiv.org/abs/2511.09965","paper_title":"Equivariant Sampling for Improving Diffusion Model-based Image Restoration","repo_url":"https://github.com/FouierL/EquS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}