Instance Shadow Detection with A Single-Stage Detector

by   Tianyu Wang, et al.

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.


page 1

page 3

page 5

page 6

page 7

page 9

page 11

page 12


Instance Shadow Detection

Instance shadow detection is a brand new problem, aiming to find shadow ...

Target Driven Instance Detection

While state-of-the-art general object detectors are getting better and b...

Object Detection Made Simpler by Eliminating Heuristic NMS

We show a simple NMS-free, end-to-end object detection framework, of whi...

PointINS: Point-based Instance Segmentation

A single-point feature has shown its effectiveness in object detection. ...

CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning

Localizing text instances in natural scenes is regarded as a fundamental...

Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection

A major impediment in rapidly deploying object detection models for inst...

Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap

Oriented object detection is a crucial task in computer vision. Current ...