{"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/style-guided-shadow-removal","title":"Style-Guided Shadow Removal","arxiv_id":null,"date":"2022-11-09","proceeding":"ECCV 2022 11","authors":["Jin Wan","Hui Yin","Zhenyao Wu","Xinyi Wu","Yanting Liu","Song Wang"],"abstract":"Shadow removal is an important topic in image restoration, and it can benefit many computer vision tasks. State-of-the-art shadow-removal methods typically employ deep learning by minimizing a pixel-level difference between the de-shadowed region and their corresponding (pseudo) shadow-free version. After shadow removal, the shadow and non-shadow regions may exhibit inconsistent appearance, leading to a visually disharmonious image. To address this problem, we propose a style-guided shadow removal network (SG-ShadowNet) for better image-style consistency after shadow removal. In SG-ShadowNet, we first learn the style representation of the non-shadow region via a simple region style estimator. Then we propose a novel effective normalization strategy with the region-level style to adjust the coarsely re-covered shadow region to be more harmonized with the rest of the image. Extensive experiments show that our proposed SG-ShadowNet outperforms all the existing competitive models and achieves a new state-of-the-art performance on ISTD+, SRD, and Video Shadow Removal benchmark datasets. Code is available at: https://github.com/jinwan1994/SG-ShadowNet.","url_abs":"https://link.springer.com/chapter/10.1007/978-3-031-19800-7_21","url_pdf":"https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136790353.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":"style-guided-shadow-removal","repo_url":"https://github.com/jinwan1994/SG-ShadowNet","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"SG-ShadowNet (ECCV 2022) (512x512)","rank_in_archive_order":5,"of":26,"metrics":{"LPIPS":"0.205","PSNR":"28.25","RMSE":"2.98","SSIM":"0.849"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-istd-1","task":"Shadow Removal","dataset":"ISTD+","model":"SG-ShadowNet (ECCV 2022) (256x256)","rank_in_archive_order":11,"of":26,"metrics":{"LPIPS":"0.369","PSNR":"26.8","RMSE":"3.32","SSIM":"0.717"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"SG-ShadowNet (ECCV 2022) (512x512)","rank_in_archive_order":8,"of":25,"metrics":{"LPIPS":"0.279","PSNR":"25.56","RMSE":"4.01","SSIM":"0.786"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-removal-on-srd","task":"Shadow Removal","dataset":"SRD","model":"SG-ShadowNet (ECCV 2022) (256x256)","rank_in_archive_order":17,"of":25,"metrics":{"LPIPS":"0.443","PSNR":"24.1","RMSE":"4.6","SSIM":"0.636"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}