Instance Shadow Detection with A Single-Stage Detector
This addresses a novel computer vision task for image analysis, but it is incremental as it builds on existing detection methods.
The paper tackles the new problem of instance shadow detection, aiming to detect shadow instances and their associated object casters in images, and shows that their single-stage detector achieves competitive performance on a newly compiled benchmark dataset, with applications in light direction estimation and photo editing.
This paper formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image. To approach this task, we first compile a new dataset with the masks for shadow instances, object instances, and shadow-object associations. We then design an evaluation metric for quantitative evaluation of the performance of instance shadow detection. Further, we design a single-stage detector to perform instance shadow detection in an end-to-end manner, where the bidirectional relation learning module and the deformable maskIoU head are proposed in the detector to directly learn the relation between shadow instances and object instances and to improve the accuracy of the predicted masks. Finally, we quantitatively and qualitatively evaluate our method on the benchmark dataset of instance shadow detection and show the applicability of our method on light direction estimation and photo editing.