NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
复制标题
DOI：
10.1109/cvprw56347.2022.00114
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Eduardo P'erez-Pellitero;Sibi Catley-Chandar;Richard Shaw;Alevs Leonardis;R. Timofte;Zexin Zhang;Cen Liu;Yunbo Peng;Yue Lin;G. Yu;Jin Zhang;Zhe Ma;Hongbin Wang;Xiangyu Chen;Xintao Wang-;Haiwei Wu;Lin Liu;Chao Dong;Jiantao Zhou;Qingsen Yan;Song Zhang;Weiye Chen;Yuhang Liu;Zhen Zhang;Yanning Zhang;Javen Qinfeng Shi;Dong Gong;Dan Zhu;Mengdi Sun;Guannan Chen;Yang Hu;Hao Li;Baozhu Zou;Zhen Liu;Wen-qing Lin;T. Jiang;Chengzhi Jiang;Xinpeng Li;Mingyan Han;Haoqiang Fan;Jian-jun Sun;Shuaicheng Liu;Juan Mar'in-Vega;M. Sloth;Peter Schneider-Kamp;R. Rottger;Chunyan Li;Longyi Bao;Gang He;Ziya Xu;Li Xu;Gen Zhan;Ming Sun;X. Wen;Junlin Li;Jin-jin Li;Chenghua Li;Ruipeng Gang;Fang Li;Chenming Liu;S. Feng;Fei Lei;R. Liu;Jun-Xia Ruan;Tianhong Dai;Wei Li;Z. Lu;Hengyan Liu;P-Y Huang;Guangyu Ren;Yonglin Luo;Chang Liu;Qiang Tu;Saisai Ma;Yi Cao;S. Tel;B. Heyrman;D. Ginhac;Chul Lee;Gahyeong Kim;Seonghyun Park;An Gia Vien;T. T. N. Mai-T.;H. Yoon;T. Vo;Alexander M. Holston;S. Zaheer;Chan-Young Park
中科院分区：
文献类型：
--
作者：
Eduardo P'erez-Pellitero;Sibi Catley-Chandar;Richard Shaw;Alevs Leonardis;R. Timofte;Zexin Zhang;Cen Liu;Yunbo Peng;Yue Lin;G. Yu;Jin Zhang;Zhe Ma;Hongbin Wang;Xiangyu Chen;Xintao Wang-;Haiwei Wu;Lin Liu;Chao Dong;Jiantao Zhou;Qingsen Yan;Song Zhang;Weiye Chen;Yuhang Liu;Zhen Zhang;Yanning Zhang;Javen Qinfeng Shi;Dong Gong;Dan Zhu;Mengdi Sun;Guannan Chen;Yang Hu;Hao Li;Baozhu Zou;Zhen Liu;Wen-qing Lin;T. Jiang;Chengzhi Jiang;Xinpeng Li;Mingyan Han;Haoqiang Fan;Jian-jun Sun;Shuaicheng Liu;Juan Mar'in-Vega;M. Sloth;Peter Schneider-Kamp;R. Rottger;Chunyan Li;Longyi Bao;Gang He;Ziya Xu;Li Xu;Gen Zhan;Ming Sun;X. Wen;Junlin Li;Jin-jin Li;Chenghua Li;Ruipeng Gang;Fang Li;Chenming Liu;S. Feng;Fei Lei;R. Liu;Jun-Xia Ruan;Tianhong Dai;Wei Li;Z. Lu;Hengyan Liu;P-Y Huang;Guangyu Ren;Yonglin Luo;Chang Liu;Qiang Tu;Saisai Ma;Yi Cao;S. Tel;B. Heyrman;D. Ginhac;Chul Lee;Gahyeong Kim;Seonghyun Park;An Gia Vien;T. T. N. Mai-T.;H. Yoon;T. Vo;Alexander M. Holston;S. Zaheer;Chan-Young Park
本文回顾了在2022年计算机视觉与模式识别会议（CVPR）期间举办的图像恢复与增强新趋势（NTIRE）研讨会上有关受限高动态范围（HDR）成像的挑战赛。本文主要关注竞赛设置、数据集、所提出的方法及其结果。该挑战赛旨在从多个相应的低动态范围（LDR）观测值中估计出一幅HDR图像，这些观测值可能存在曝光不足或过度的区域以及不同的噪声源。该挑战赛由两个赛道组成，重点关注保真度和复杂度限制：在赛道1中，要求参赛者在施加低复杂度限制的情况下优化客观保真度得分（即解决方案的运算次数不能超过给定数量）。在赛道2中，要求参赛者在对保真度得分施加限制的情况下最小化其解决方案的复杂度（即解决方案需要获得比规定基线更高的保真度得分）。两个赛道使用相同的数据和指标：保真度通过相对于真实HDR图像的峰值信噪比（PSNR）来衡量（直接计算以及通过标准色调映射操作计算），而复杂度指标包括乘累加（MAC）运算次数和运行时间（以秒为单位）。
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).