MRDN: A lightweight Multi-stage residual distillation network for image Super-Resolution

作者：

Highlights：

• Constructing a multi-stage residual distillation network for lightweight SR.

• Designing an efficient pixel attention module.

• Constructing a multi-stage residual distillation block.

• Effectively reducing the network parameters.

• Superior to the state-of-the-art models.

摘要

•Constructing a multi-stage residual distillation network for lightweight SR.•Designing an efficient pixel attention module.•Constructing a multi-stage residual distillation block.•Effectively reducing the network parameters.•Superior to the state-of-the-art models.

论文关键词：Image super-resolution,Lightweight network,Multilevel residual distillation,Efficient pixel attention,Mobile client

论文评审过程：Received 28 May 2021, Revised 12 May 2022, Accepted 12 May 2022, Available online 16 May 2022, Version of Record 26 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117594