Highlight Removal from A Single Grayscale Image Using Attentive GAN
The existence of specular highlights hinders high-level computer algorithms. In this paper, we propose a novel approach to remove specular highlights from a single grayscale image by regarding the problem as an image-to-image translation task between the highlight domain and the diffuse domain. We s...
| Auteurs principaux: | , , |
|---|---|
| Format: | Article |
| Langue: | English |
| Publié: |
Taylor & Francis Group
2022-12-01
|
| Collection: | Applied Artificial Intelligence |
| Accès en ligne: | http://dx.doi.org/10.1080/08839514.2021.1988441 |