NTIRE 2021 感知图像质量评价挑战赛
图像与视频处理
2021-06-29 v3 计算机视觉与模式识别
摘要
本文报道了 NTIRE 2021 感知图像质量评价（IQA）挑战赛，该赛事与 CVPR 2021 上的图像恢复与增强新趋势研讨会（NTIRE）联合举办。作为一种新型图像处理技术，基于生成对抗网络（GAN）的感知图像处理算法已生成具有更真实纹理的图像。这些输出图像具有与传统失真完全不同的特性，从而对 IQA 方法评估其视觉质量提出了新挑战。与以往的 IQA 挑战赛相比，本次挑战赛的训练与测试数据集包含了感知图像处理算法的输出及相应的主观评分。因此它们可用于开发和评估针对基于 GAN 失真的 IQA 方法。该挑战赛共有 270 名注册参与者。在最终测试阶段，13 支参赛队伍提交了他们的模型与事实表。几乎所有队伍都取得了远优于现有 IQA 方法的结果，而优胜方法展示了最先进的性能。
引用
@article{arxiv.2105.03072,
title = {NTIRE 2021 Challenge on Perceptual Image Quality Assessment},
author = {Jinjin Gu and Haoming Cai and Chao Dong and Jimmy S. Ren and Yu Qiao and Shuhang Gu and Radu Timofte and Manri Cheon and Sungjun Yoon and Byungyeon Kang and Junwoo Lee and Qing Zhang and Haiyang Guo and Yi Bin and Yuqing Hou and Hengliang Luo and Jingyu Guo and Zirui Wang and Hai Wang and Wenming Yang and Qingyan Bai and Shuwei Shi and Weihao Xia and Mingdeng Cao and Jiahao Wang and Yifan Chen and Yujiu Yang and Yang Li and Tao Zhang and Longtao Feng and Yiting Liao and Junlin Li and William Thong and Jose Costa Pereira and Ales Leonardis and Steven McDonagh and Kele Xu and Lehan Yang and Hengxing Cai and Pengfei Sun and Seyed Mehdi Ayyoubzadeh and Ali Royat and Sid Ahmed Fezza and Dounia Hammou and Wassim Hamidouche and Sewoong Ahn and Gwangjin Yoon and Koki Tsubota and Hiroaki Akutsu and Kiyoharu Aizawa},
journal= {arXiv preprint arXiv:2105.03072},
year = {2021}
}