{"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/instance-shadow-detection","title":"Instance Shadow Detection","arxiv_id":"1911.07034","date":"2019-11-16","proceeding":"CVPR 2020 6","authors":["Tianyu Wang","Xiao-Wei Hu","Qiong Wang","Pheng-Ann Heng","Chi-Wing Fu"],"abstract":"Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks. Second, we design LISA, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the shadow-object associations and light direction. Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results. In our evaluations, we formulate a new metric named the shadow-object average precision to measure the performance of our results. Further, we conducted various experiments and demonstrate our method's applicability on light direction estimation and photo editing.","url_abs":"https://arxiv.org/abs/1911.07034v2","url_pdf":"https://arxiv.org/pdf/1911.07034v2.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":"instance-shadow-detection","repo_url":"https://github.com/BalajSaleem/InstanceShadowDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"instance-shadow-detection","repo_url":"https://github.com/gmlee329/InstanceShadowDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"instance-shadow-detection","repo_url":"https://github.com/stevewongv/InstanceShadowDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-shadow-detection","task_name":"Instance Shadow Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"shadow-detection","task_name":"Shadow Detection"}],"methods":[],"datasets_introduced":[{"slug":"soba","name":"SOBA","full_name":"Shadow-OBject Association"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-shadow-detection-on-soba","task":"Instance Shadow Detection","dataset":"SOBA","model":"LISA (CVPR 2020)","rank_in_archive_order":3,"of":3,"metrics":{"Asso. AP_bbox":"50.4","Asso. AP_segm":"42.7","Bounding Box SOAP":"21.9","Instance AP_bbox":"38.2","Instance AP_segm":"39.7","mask SOAP":"23.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.07034","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}