Name
Abstract | ||
|---|---|---|
Shadow removal is an important yet challenging task in image processing and computer vision. Existing methods are limited in extracting good global features due to the interference of shadow. And also, most of them ignore a fact that features inside and outside the shaded area should be treated disparately because of different semantics or materials. In this letter, we propose a novel deep neural network Mask-ShadowNet for shadow removal. The core of our approach is a well-designed masked adaptive instance normalization (MAdaIN) mechanism with embedded aligners that serves two goals: 1) producing hidden features that considering an illumination consistency of different regions. 2) treating the feature statistics of shadow and non-shadow areas discriminately based on the shadow mask. Experimental results demonstrate that the proposed model outperforms the state-of-the-art on the ISTD benchmark. Our code is available in https://github.com/penguinbing/Mask-ShadowNet. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/LSP.2021.3074082 | IEEE SIGNAL PROCESSING LETTERS |
Keywords | DocType | Volume |
Lighting, Feature extraction, Training, Neural networks, Task analysis, Predictive models, Adaptation models, Deep neural network, shadow removal, masked adaptive instance normalization | Journal | 28 |
ISSN | Citations | PageRank |
1070-9908 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shengfeng He | 1 | 406 | 33.19 |
| Bing Peng | 2 | 0 | 0.34 |
| Junyu Dong | 3 | 0 | 0.68 |
| Yong Du | 4 | 3 | 2.07 |