NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
Abstract
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from 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 of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).
Cite
@article{arxiv.2205.12633,
title = {NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results},
author = {Eduardo Pérez-Pellitero and Sibi Catley-Chandar and Richard Shaw and Aleš Leonardis and Radu Timofte and Zexin Zhang and Cen Liu and Yunbo Peng and Yue Lin and Gaocheng Yu and Jin Zhang and Zhe Ma and Hongbin Wang and Xiangyu Chen and Xintao Wang and Haiwei Wu and Lin Liu and Chao Dong and Jiantao Zhou and Qingsen Yan and Song Zhang and Weiye Chen and Yuhang Liu and Zhen Zhang and Yanning Zhang and Javen Qinfeng Shi and Dong Gong and Dan Zhu and Mengdi Sun and Guannan Chen and Yang Hu and Haowei Li and Baozhu Zou and Zhen Liu and Wenjie Lin and Ting Jiang and Chengzhi Jiang and Xinpeng Li and Mingyan Han and Haoqiang Fan and Jian Sun and Shuaicheng Liu and Juan Marín-Vega and Michael Sloth and Peter Schneider-Kamp and Richard Röttger and Chunyang Li and Long Bao and Gang He and Ziyao Xu and Li Xu and Gen Zhan and Ming Sun and Xing Wen and Junlin Li and Jinjing Li and Chenghua Li and Ruipeng Gang and Fangya Li and Chenming Liu and Shuang Feng and Fei Lei and Rui Liu and Junxiang Ruan and Tianhong Dai and Wei Li and Zhan Lu and Hengyan Liu and Peian Huang and Guangyu Ren and Yonglin Luo and Chang Liu and Qiang Tu and Fangya Li and Ruipeng Gang and Chenghua Li and Jinjing Li and Sai Ma and Chenming Liu and Yizhen Cao and Steven Tel and Barthelemy Heyrman and Dominique Ginhac and Chul Lee and Gahyeon Kim and Seonghyun Park and An Gia Vien and Truong Thanh Nhat Mai and Howoon Yoon and Tu Vo and Alexander Holston and Sheir Zaheer and Chan Y. Park},
journal= {arXiv preprint arXiv:2205.12633},
year = {2022}
}
Comments
CVPR Workshops 2022. 15 pages, 21 figures, 2 tables