Instance Shadow Detection with A Single-Stage Detector

Abstract

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.

arXiv commentAccepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). This is the journal version of arXiv:1911.07034 and https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_Single-Stage_Instance_Shadow_Detection_With_Bidirectional_Relation_Learning_CVPR_2021_paper.pdf

References in corpus (6)

• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Direction-aware Spatial Context Features for Shadow Detection
• Direction-aware Spatial Context Features for Shadow Detection and Removal
• Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data
• Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data
• Revisiting Shadow Detection: A New Benchmark Dataset for Complex World