{"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/learning-from-synthetic-shadows-for-shadow","title":"Learning from Synthetic Shadows for Shadow Detection and Removal","arxiv_id":"2101.01713","date":"2021-01-05","proceeding":null,"authors":["Naoto Inoue","Toshihiko Yamasaki"],"abstract":"Shadow removal is an essential task in computer vision and computer graphics. Recent shadow removal approaches all train convolutional neural networks (CNN) on real paired shadow/shadow-free or shadow/shadow-free/mask image datasets. However, obtaining a large-scale, diverse, and accurate dataset has been a big challenge, and it limits the performance of the learned models on shadow images with unseen shapes/intensities. To overcome this challenge, we present SynShadow, a novel large-scale synthetic shadow/shadow-free/matte image triplets dataset and a pipeline to synthesize it. We extend a physically-grounded shadow illumination model and synthesize a shadow image given an arbitrary combination of a shadow-free image, a matte image, and shadow attenuation parameters. Owing to the diversity, quantity, and quality of SynShadow, we demonstrate that shadow removal models trained on SynShadow perform well in removing shadows with diverse shapes and intensities on some challenging benchmarks. Furthermore, we show that merely fine-tuning from a SynShadow-pre-trained model improves existing shadow detection and removal models. Codes are publicly available at https://github.com/naoto0804/SynShadow.","url_abs":"https://arxiv.org/abs/2101.01713v2","url_pdf":"https://arxiv.org/pdf/2101.01713v2.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":"learning-from-synthetic-shadows-for-shadow","repo_url":"https://github.com/naoto0804/SynShadow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"shadow-detection","task_name":"Shadow Detection"},{"task_slug":"shadow-detection-and-removal","task_name":"Shadow Detection And Removal"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.01713","atlas_url":"https://app.syntology.ai/?focus=2101.01713","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}