Paper Info
Title
S<sup>2</sup>Net: Shadow Mask-Based Semantic-Aware Network for Single-Image Shadow Removal
Abstract
Existing shadow removal methods often struggle with two problems: color inconsistencies in shadow areas and artifacts along shadow boundaries. To address these two problems, we propose a novel shadow mask-based semantic-aware network (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> Net) that uses shadow masks as guidance for shadow removal. The color inconsistency problem is solved in two steps. First, we use a series of semantic-guided dilated residual (SDR) blocks to transfer statistical information from non-shadow areas to shadow areas. The shadow mask-based semantic transformation (SST) operation in SDR enables the network to remove shadows while keeping non-shadow areas intact. Then, we design a refinement block by incorporating semantic knowledge of shadow masks and applying the learned modulated convolution kernels to get traceless and consistent output. To remove artifacts along shadow boundaries, we propose a newly designed boundary loss. The boundary loss encourages spatial coherence around shadow boundaries. By including the boundary loss as part of the loss function, a significant portion of artifacts along shadow boundaries can be removed. Extensive experiments on the ISTD, ISTD+, SRD and SBU datasets show our S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> Net outperforms existing shadow removal methods.
Year
DOI
Venue
2022
10.1109/TCE.2022.3188968
IEEE Transactions on Consumer Electronics
Keywords
DocType
Volume
Shadow removal,semantic-guided feature extraction,semantic transformation,refinement,boundary loss
Journal
68
Issue
ISSN
Citations 
3
0098-3063
0
PageRank 
References 
Authors
0.34
11
5
Name
Order
Citations
PageRank
Qiqi Bao112.38
Yunmeng Liu200.34
Bowen Gang301.35
WM422134.28
QM546472.05