Relighting Humans in the Wild: Monocular Full-Body Human Relighting with Domain Adaptation
| dc.contributor.author | Tajima, Daichi | en_US |
| dc.contributor.author | Kanamori, Yoshihiro | en_US |
| dc.contributor.author | Endo, Yuki | en_US |
| dc.contributor.editor | Zhang, Fang-Lue and Eisemann, Elmar and Singh, Karan | en_US |
| dc.date.accessioned | 2021-10-14T11:12:04Z | |
| dc.date.available | 2021-10-14T11:12:04Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | The modern supervised approaches for human image relighting rely on training data generated from 3D human models. However, such datasets are often small (e.g., Light Stage data with a small number of individuals) or limited to diffuse materials (e.g., commercial 3D scanned human models). Thus, the human relighting techniques suffer from the poor generalization capability and synthetic-to-real domain gap. In this paper, we propose a two-stage method for single-image human relighting with domain adaptation. In the first stage, we train a neural network for diffuse-only relighting. In the second stage, we train another network for enhancing non-diffuse reflection by learning residuals between real photos and images reconstructed by the diffuse-only network. Thanks to the second stage, we can achieve higher generalization capability against various cloth textures, while reducing the domain gap. Furthermore, to handle input videos, we integrate illumination-aware deep video prior to greatly reduce flickering artifacts even with challenging settings under dynamic illuminations. | en_US |
| dc.description.number | 7 | |
| dc.description.sectionheaders | Image Synthesis and Enhancement | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 40 | |
| dc.identifier.doi | 10.1111/cgf.14414 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 205-216 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.14414 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf14414 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Image manipulation | |
| dc.subject | Neural networks | |
| dc.title | Relighting Humans in the Wild: Monocular Full-Body Human Relighting with Domain Adaptation | en_US |