{"componentChunkName":"component---src-templates-publication-js","path":"/research/instance-shadow-cvpr2020/","result":{"pageContext":{"publication":{"id":"instance-shadow-cvpr2020","title":"Instance Shadow Detection","authors":["Tianyu Wang","Xiaowei Hu","Qiong Wang","Pheng-Ann Heng","Chi-Wing Fu"],"highlightAuthor":"Tianyu Wang","venue":"CVPR","year":2020,"tldr":"First work to tackle instance-level shadow detection, associating each shadow with its corresponding object instance.","links":{"paper":"https://arxiv.org/abs/1911.07034","dataset":"https://drive.google.com/drive/folders/1MKxyq3R6AUeyLai9i9XWzG2C_n5f0ppP","code":"https://github.com/stevewongv/InstanceShadowDetection"},"insight":"Defines the new task of instance shadow detection--pairing each shadow with its casting object--and introduces the SOBA dataset and LISA framework as foundational benchmarks for the field.","teaser":"/images/information/lisa.png","bibtex":"@InProceedings{Wang_2020_CVPR,\n  author = {Wang, Tianyu and Hu, Xiaowei and Wang, Qiong and Heng, Pheng-Ann and Fu, Chi-Wing},\n  title = {Instance Shadow Detection},\n  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n  month = {June},\n  year = {2020}\n}","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.","abstractSource":"https://arxiv.org/abs/1911.07034","version":"arXiv version linked; publication venue as listed above"}}},"staticQueryHashes":["63159454"]}