Self-supervised cycle-consistent learning for scale-arbitrary real-world single image super-resolution
作者：
Highlights：
• We propose a self-learning-based scale-arbitrary SR method for real-world images.
• Scale-arbitrary SR and resolution-degradation networks are jointly optimized.
• The cycle consistency, bicubic interpolation, and total variation losses are adopted.
• We enable a parameter to adjust perceptual quality to satisfy users’ preferences.
• Extensive experiments are conducted to demonstrate the effectiveness of our method.
摘要
•We propose a self-learning-based scale-arbitrary SR method for real-world images.•Scale-arbitrary SR and resolution-degradation networks are jointly optimized.•The cycle consistency, bicubic interpolation, and total variation losses are adopted.•We enable a parameter to adjust perceptual quality to satisfy users’ preferences.•Extensive experiments are conducted to demonstrate the effectiveness of our method.
论文关键词：Real-world image,Super-resolution,Resolution-degradation,Self-supervised cycle-consistent learning,Arbitrary scaling factors,Convolutional neural networks
论文评审过程：Received 21 March 2022, Revised 15 July 2022, Accepted 20 August 2022, Available online 28 August 2022, Version of Record 6 September 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118657
