NTIRE 2021 Challenge on Perceptual Image Quality Assessment
This addresses the problem of assessing image quality for GAN-generated outputs in computer vision, but it is incremental as it builds on previous IQA challenges by introducing new datasets.
The paper tackled the challenge of evaluating visual quality for images generated by GAN-based perceptual processing, which have different characteristics from traditional distortions, by organizing the NTIRE 2021 challenge with datasets including these outputs and subjective scores, resulting in 13 teams submitting models that outperformed existing IQA methods, with the winner achieving state-of-the-art performance.
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 new 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.