{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/shadowdiffusion-when-degradation-prior-meets","title":"ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal","arxiv_id":"2212.04711","date":"2022-12-09","proceeding":"CVPR 2023 1","authors":["Lanqing Guo","Chong Wang","Wenhan Yang","Siyu Huang","YuFei Wang","Hanspeter Pfister","Bihan Wen"],"abstract":"Recent deep learning methods have achieved promising results in image shadow removal. However, their restored images still suffer from unsatisfactory boundary artifacts, due to the lack of degradation prior embedding and the deficiency in modeling capacity. Our work addresses these issues by proposing a unified diffusion framework that integrates both the image and degradation priors for highly effective shadow removal. In detail, we first propose a shadow degradation model, which inspires us to build a novel unrolling diffusion model, dubbed ShandowDiffusion. It remarkably improves the model's capacity in shadow removal via progressively refining the desired output with both degradation prior and diffusive generative prior, which by nature can serve as a new strong baseline for image restoration. Furthermore, ShadowDiffusion progressively refines the estimated shadow mask as an auxiliary task of the diffusion generator, which leads to more accurate and robust shadow-free image generation. We conduct extensive experiments on three popular public datasets, including ISTD, ISTD+, and SRD, to validate our method's effectiveness. Compared to the state-of-the-art methods, our model achieves a significant improvement in terms of PSNR, increasing from 31.69dB to 34.73dB over SRD dataset.","url_abs":"https://arxiv.org/abs/2212.04711v2","url_pdf":"https://arxiv.org/pdf/2212.04711v2.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":"shadowdiffusion-when-degradation-prior-meets","repo_url":"https://github.com/GuoLanqing/ShadowDiffusion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-shadow-removal","task_name":"Image Shadow Removal"},{"task_slug":"unrolling","task_name":"Rolling Shutter Correction"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"ShadowDiffusion\n  (CVPR 2023) (512x512)","rank_in_archive_order":9,"of":26,"metrics":{"LPIPS":"0.222","PSNR":"27.87","RMSE":"3.1","SSIM":"0.839"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"ShadowDiffusion (CVPR 2023) (256x256)","rank_in_archive_order":19,"of":26,"metrics":{"LPIPS":"0.404","PSNR":"26.51","RMSE":"3.44","SSIM":"0.688"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"ShadowDiffusion (CVPR 2023) (256x256)","rank_in_archive_order":20,"of":25,"metrics":{"LPIPS":"0.363","PSNR":"23.26","RMSE":"4.84","SSIM":"0.684"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"ShadowDiffusion (CVPR 2023) (512x512)","rank_in_archive_order":21,"of":25,"metrics":{"LPIPS":"0.24","PSNR":"23.09","RMSE":"5.11","SSIM":"0.804"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.04711","atlas_url":"https://app.syntology.ai/?focus=2212.04711","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2212.04711"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.04711\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.04711"},"call":"get_concepts_for_paper(arxiv_id=\"2212.04711\")"}],"by_repo":[{"repo":"GuoLanqing/ShadowDiffusion","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7b6b31d1441f878eaafdc42669c010ffbb9c57f06311b765856bba68503fa34c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}