NTIRE 2021 Challenge on Perceptual Image Quality Assessment [article]

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
2021 arXiv   pre-print
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of image processing technology, perceptual image processing algorithms based on Generative Adversarial Networks (GAN) have produced images with more realistic textures. These output images have completely different characteristics from traditional distortions, thus pose a
more » ... challenge for IQA methods to evaluate their visual quality. In comparison with previous IQA challenges, the training and testing datasets in this challenge include the outputs of perceptual image processing algorithms and the corresponding subjective scores. Thus they can be used to develop and evaluate IQA methods on GAN-based distortions. The challenge has 270 registered participants in total. In the final testing stage, 13 participating teams submitted their models and fact sheets. Almost all of them have achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.
arXiv:2105.03072v3 fatcat:mf4q3hvz4jbepgyhkzg7wbylqq