An efficient image super resolution model with dense skip connections between complex filter structures in Generative Adversarial Networks
作者：
Highlights：
• Proposed an Generative Adversarial Network based model for image super resolution.
• Primitive and hierarchical feature learning with Complex filter structure.
• Dense skip connections are introduced to increase the learning capability.
• Progressive upscaling approach is used to obtain fine texture details.
• Performance is evaluated with the state-of-the-art methods.
摘要
•Proposed an Generative Adversarial Network based model for image super resolution.•Primitive and hierarchical feature learning with Complex filter structure.•Dense skip connections are introduced to increase the learning capability.•Progressive upscaling approach is used to obtain fine texture details.•Performance is evaluated with the state-of-the-art methods.
论文关键词：Super resolution,Convolutional neural networks,Generative adversarial networks,Inception architecture,Subpixel layer
论文评审过程：Received 26 February 2020, Revised 5 December 2020, Accepted 14 August 2021, Available online 22 August 2021, Version of Record 27 August 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115780
