{"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/physics-based-shadow-image-decomposition-for","title":"Physics-based Shadow Image Decomposition for Shadow Removal","arxiv_id":"2012.13018","date":"2020-12-23","proceeding":null,"authors":["Hieu Le","Dimitris Samaras"],"abstract":"We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects from images. We then employ an inpainting network, I-Net, to further refine the results. We train and test our framework on the most challenging shadow removal dataset (ISTD). Our method improves the state-of-the-art in terms of root mean square error (RMSE) for the shadow area by 20\\%. Furthermore, this decomposition allows us to formulate a patch-based weakly-supervised shadow removal method. This model can be trained without any shadow-free images (that are cumbersome to acquire) and achieves competitive shadow removal results compared to state-of-the-art methods that are trained with fully paired shadow and shadow-free images. Last, we introduce SBU-Timelapse, a video shadow removal dataset for evaluating shadow removal methods.","url_abs":"https://arxiv.org/abs/2012.13018v2","url_pdf":"https://arxiv.org/pdf/2012.13018v2.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":"physics-based-shadow-image-decomposition-for","repo_url":"https://github.com/cvlab-stonybrook/SID","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"physics-based-shadow-image-decomposition-for","repo_url":"https://github.com/lmhieu612/SID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[{"method_slug":"pixel-prediction","method_name":"Inpainting"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.13018","atlas_url":"https://app.syntology.ai/?focus=2012.13018","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}