학술논문
NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results
Document Type
Conference
Author
Perez-Pellitero, Eduardo; Catley-Chandar, Sibi; Leonardis, Ales; Timofte, Radu; Wang, Xian; Li, Yong; Wang, Tao; Song, Fenglong; Liu, Zhen; Lin, Wenjie; Li, Xinpeng; Rao, Qing; Jiang, Ting; Han, Mingyan; Fan, Haoqiang; Sun, Jian; Liu, Shuaicheng; Chen, Xiangyu; Liu, Yihao; Zhang, Zhengwen; Qiao, Yu; Dong, Chao; Lyn Chee, Evelyn Yi; Shen, Shanlan; Duan, Yubo; Chen, Guannan; Sun, Mengdi; Gao, Yan; Zhang, Lijie; A, Akhil K; V, Jiji C; Sharif, S M A; Naqvi, Rizwan Ali; Biswas, Mithun; Kim, Sungjun; Xia, Chenjie; Zhao, Bowen; Ye, Zhangyu; Lu, Xiwen; Cao, Yanpeng; Yang, Jiangxin; Cao, Yanlong; S, Green Rosh K; Deepak Lomte, Sachin; Krishnan, Nikhil; Pawan Prasad, B H
Source
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) CVPRW Computer Vision and Pattern Recognition Workshops (CVPRW), 2021 IEEE/CVF Conference on. :691-700 Jun, 2021
Subject
Language
ISSN
2160-7516
Abstract
This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021. This manuscript focuses on the newly introduced dataset, the proposed methods and their results. The challenge aims at estimating a HDR image from one or multiple respective low-dynamic range (LDR) observations, which might suffer from under-or over-exposed regions and different sources of noise. The challenge is composed by two tracks: In Track 1 only a single LDR image is provided as input, whereas in Track 2 three differently-exposed LDR images with inter-frame motion are available. In both tracks, the ultimate goal is to achieve the best objective HDR reconstruction in terms of PSNR with respect to a ground-truth image, evaluated both directly and with a canonical tonemapping operation.