BROWSE
Detail
Journal Article
C2ShadowGAN: cycle-in-cycle generative adversarial network for shadow removal using unpaired data
- Authors
- Sunwon Kang, Juwan Kim, In Sung Jang, Byoung-Dai Lee
- Issue Date
- 2023-06
- Citation
- Applied Intelligence, v.53, no.12, pp.15067-15079
- ISSN
- 0924-669X
- Publisher
- Kluwer Academic Publishers
- Language
- English
- Type
- Journal Article
- Abstract
- Recent advances in deep learning technology, and the availability of public shadow image datasets, have enabled significant performance improvements of shadow removal tasks in computer vision. However, most deep learning-based shadow removal methods are usually trained in a supervised manner, in which paired shadow and shadow-free data are required. We developed a weakly supervised generative adversarial network with a cycle-in-cycle structure for shadow removal using unpaired data. In addition, we introduced new loss functions to reduce unnecessary transformations for non-shadow areas and to enable smooth transformations for shadow boundary areas. We conducted extensive experiments using the ISTD and Video Shadow Removal datasets to assess the effectiveness of our methods. The experimental results show that our method is superior to other state-of-the-art methods trained on unpaired data.
- KSP Keywords
- Boundary areas, Computer Vision(CV), Cycle Structure, Free Data, Learning Technology, Learning-based, Shadow boundary, Weakly supervised, deep learning(DL), generative adversarial network, image datasets
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
