Instance Shadow Detection
This addresses the problem of detecting shadows and their associated objects in images for applications like photo editing, though it is incremental as it builds on existing shadow detection work.
The paper tackles the new problem of instance shadow detection, which involves finding shadow instances paired with object instances, by introducing the SOBA dataset with 3,623 pairs and the LISA framework, achieving results measured with a new shadow-object average precision metric.
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.