Shadow Inpainting and Removal Using Generative Adversarial Networks with Slice Convolutions
| dc.contributor.author | Wei, Jinjiang | en_US |
| dc.contributor.author | Long, Chengjiang | en_US |
| dc.contributor.author | Zou, Hua | en_US |
| dc.contributor.author | Xiao, Chunxia | en_US |
| dc.contributor.editor | Lee, Jehee and Theobalt, Christian and Wetzstein, Gordon | en_US |
| dc.date.accessioned | 2019-10-14T05:08:25Z | |
| dc.date.available | 2019-10-14T05:08:25Z | |
| dc.date.issued | 2019 | |
| dc.description.abstract | In this paper, we propose a two-stage top-down and bottom-up Generative Adversarial Networks (TBGANs) for shadow inpainting and removal which uses a novel top-down encoder and a bottom-up decoder with slice convolutions. These slice convolutions can effectively extract and restore the long-range spatial information for either down-sampling or up-sampling. Different from the previous shadow removal methods based on deep learning, we propose to inpaint shadow to handle the possible dark shadows to achieve a coarse shadow-removal image at the first stage, and then further recover the details and enhance the color and texture details with a non-local block to explore both local and global inter-dependencies of pixels at the second stage. With such a two-stage coarse-to-fine processing, the overall effect of shadow removal is greatly improved, and the effect of color retention in non-shaded areas is significant. By comparing with a variety of mainstream shadow removal methods, we demonstrate that our proposed method outperforms the state-of-the-art methods. | en_US |
| dc.description.number | 7 | |
| dc.description.sectionheaders | Generative Models | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 38 | |
| dc.identifier.doi | 10.1111/cgf.13845 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 381-392 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.13845 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf13845 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Shadow Inpainting | |
| dc.subject | Shadow Removal | |
| dc.subject | Top | |
| dc.subject | down | |
| dc.subject | Bottom | |
| dc.subject | up | |
| dc.subject | Slice Convolution | |
| dc.subject | Non | |
| dc.subject | local Block | |
| dc.subject | Generative Adversarial Networks | |
| dc.title | Shadow Inpainting and Removal Using Generative Adversarial Networks with Slice Convolutions | en_US |