Single-Image super-resolution - When model adaptation matters
作者：
Highlights：
• In this paper, we propose a variation of deep residual convolutional neural networks with robustness and efficiency in both learning and testing.
• More importantly, we propose multiple strategies for model adaptation to the internal contents of the lowresolution input image and analyze their strong points and weaknesses.
• Our adaptation especially favors images with repetitive structures or high resolutions.
• We hope to arouse the interests of communities in focusing on internal priors, which are limited but have been proved effective and highly relevant.
摘要
•In this paper, we propose a variation of deep residual convolutional neural networks with robustness and efficiency in both learning and testing.•More importantly, we propose multiple strategies for model adaptation to the internal contents of the lowresolution input image and analyze their strong points and weaknesses.•Our adaptation especially favors images with repetitive structures or high resolutions.•We hope to arouse the interests of communities in focusing on internal priors, which are limited but have been proved effective and highly relevant.
论文关键词：Internal prior,Model adaptation,Deep convolutional neural network,Projection skip connection
论文评审过程：Received 10 December 2019, Revised 6 August 2020, Accepted 2 March 2021, Available online 17 March 2021, Version of Record 13 April 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.107931
