https://scholars.lib.ntu.edu.tw/handle/123456789/632326
標題: | Explorable tone mapping operators | 作者: | Su C.-C Wang R Lin H.-J Liu Y.-L Chen C.-P Chang Y.-L SOO-CHANG PEI |
公開日期: | 2020 | 起(迄)頁: | 10320-10326 | 來源出版物: | Proceedings - International Conference on Pattern Recognition | 摘要: | Tone-mapping plays an essential role in high dynamic range (HDR) imaging. It aims to preserve visual information of HDR images in a medium with a limited dynamic range. Although many works have been proposed to provide tone-mapped results from HDR images, most of them can only perform tone-mapping in a single pre-designed way. However, the subjectivity of tone-mapping quality varies from person to person, and the preference of tone-mapping style also differs from application to application. In this paper, a learning-based multimodal tone-mapping method is proposed, which not only achieves excellent visual quality but also explores the style diversity. Based on the framework of BicycleGAN [1], the proposed method can provide a variety of expert-level tone-mapped results by manipulating different latent codes. Finally, we show that the proposed method performs favorably against state-of-the-art tone-mapping algorithms both quantitatively and qualitatively. © 2020 IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85110461387&doi=10.1109%2fICPR48806.2021.9412070&partnerID=40&md5=2e475c4dda714ddb87cecd143dc3c7a5 https://scholars.lib.ntu.edu.tw/handle/123456789/632326 |
ISSN: | 10514651 | DOI: | 10.1109/ICPR48806.2021.9412070 | SDG/關鍵字: | Conformal mapping; High dynamic range; Limited dynamic ranges; Multi-modal; State of the art; Tone mapping; Tone mapping operators; Visual information; Visual qualities; Pattern recognition |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。