Neural component search for single image super-resolution

作者：

Highlights：

• NCS takes the loss functions and color space as part of the search space.

• ARDN is designed with the thought of parameter sharing to speed up the search time.

• NCS can be utilized as a framework to search for new super-resolution networks.

摘要

•NCS takes the loss functions and color space as part of the search space.•ARDN is designed with the thought of parameter sharing to speed up the search time.•NCS can be utilized as a framework to search for new super-resolution networks.

论文关键词：Neural component search,Super-resolution,Reinforcement learning

论文评审过程：Received 22 September 2021, Revised 5 April 2022, Accepted 18 April 2022, Available online 30 April 2022, Version of Record 17 May 2022.

论文官网地址：https://doi.org/10.1016/j.image.2022.116725