{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dereflection-any-image-with-diffusion-priors","title":"Dereflection Any Image with Diffusion Priors and Diversified Data","arxiv_id":"2503.17347","date":"2025-03-21","proceeding":null,"authors":["Jichen Hu","Chen Yang","Zanwei Zhou","Jiemin Fang","Xiaokang Yang","Qi Tian","Wei Shen"],"abstract":"Reflection removal of a single image remains a highly challenging task due to the complex entanglement between target scenes and unwanted reflections. Despite significant progress, existing methods are hindered by the scarcity of high-quality, diverse data and insufficient restoration priors, resulting in limited generalization across various real-world scenarios. In this paper, we propose Dereflection Any Image, a comprehensive solution with an efficient data preparation pipeline and a generalizable model for robust reflection removal. First, we introduce a dataset named Diverse Reflection Removal (DRR) created by randomly rotating reflective mediums in target scenes, enabling variation of reflection angles and intensities, and setting a new benchmark in scale, quality, and diversity. Second, we propose a diffusion-based framework with one-step diffusion for deterministic outputs and fast inference. To ensure stable learning, we design a three-stage progressive training strategy, including reflection-invariant finetuning to encourage consistent outputs across varying reflection patterns that characterize our dataset. Extensive experiments show that our method achieves SOTA performance on both common benchmarks and challenging in-the-wild images, showing superior generalization across diverse real-world scenes.","url_abs":"https://arxiv.org/abs/2503.17347v1","url_pdf":"https://arxiv.org/pdf/2503.17347v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dereflection-any-image-with-diffusion-priors","repo_url":"https://github.com/Abuuu122/Dereflection-Any-Image","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"reflection-removal","task_name":"Reflection Removal"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/reflection-removal-on-nature","task":"Reflection Removal","dataset":"Nature","model":"DAI","rank_in_archive_order":1,"of":5,"metrics":{"PSNR":"26.81","SSIM":"0.843"},"uses_additional_data":false},{"leaderboard":"/sota/reflection-removal-on-real20","task":"Reflection Removal","dataset":"Real20","model":"DAI","rank_in_archive_order":2,"of":8,"metrics":{"PSNR":"25.21","SSIM":"0.841"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.17347","atlas_url":"https://app.syntology.ai/?focus=2503.17347","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}