Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2017

Abstract

Shadow removal is a challenging task as it requires the detection/annotation of shadows as well as semantic understanding of the scene. In this paper, we propose an automatic and end-to-end deep neural network (DeshadowNet) to tackle these problems in a unified manner. DeshadowNet is designed with a multi-context architecture, where the output shadow matte is predicted by embedding information from three different perspectives. The first global network extracts shadow features from a global view. Two levels of features are derived from the global network and transferred to two parallel networks. While one extracts the appearance of the input image, the other one involves semantic understanding for final prediction. These two complementary networks generate multi-context features to obtain the shadow matte with fine local details. To evaluate the performance of the proposed method, we construct the first large scale benchmark with 3088 image pairs. Extensive experiments on two publicly available benchmarks and our large-scale benchmark show that the proposed method performs favorably against several state-of-the-art methods.

Keywords

Benchmarking, Computer vision, Deep neural networks, Image segmentation, Semantics

Discipline

Artificial Intelligence and Robotics | OS and Networks | Systems Architecture

Research Areas

Software and Cyber-Physical Systems

Publication

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, Hawaii, USA, July 21-26

First Page

2308

Last Page

2316

ISBN

9781538604571

Identifier

10.1109/CVPR.2017.248

Publisher

IEEE

City or Country

New York, NY, USA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2017.248

Download

Share

COinS