Frequency-Based Enhancement Network for Efficient Super-Resolution

Parichehr Behjati, Pau Rodriguez, Carles Fernandez Tena, Armin Mehri, F. Xavier Roca, Seiichi Ozawa, Jordi Gonzalez

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)


Recently, deep convolutional neural networks (CNNs) have provided outstanding performance in single image super-resolution (SISR). Despite their remarkable performance, the lack of high-frequency information in the recovered images remains a core problem. Moreover, as the networks increase in depth and width, deep CNN-based SR methods are faced with the challenge of computational complexity in practice. A promising and under-explored solution is to adapt the amount of compute based on the different frequency bands of the input. To this end, we present a novel Frequency-based Enhancement Block (FEB) which explicitly enhances the information of high frequencies while forwarding low-frequencies to the output. In particular, this block efficiently decomposes features into low- and high-frequency and assigns more computation to high-frequency ones. Thus, it can help the network generate more discriminative representations by explicitly recovering finer details. Our FEB design is simple and generic and can be used as a direct replacement of commonly used SR blocks with no need to change network architectures. We experimentally show that when replacing SR blocks with FEB we consistently improve the reconstruction error, while reducing the number of parameters in the model. Moreover, we propose a lightweight SR model - Frequency-based Enhancement Network (FENet) - based on FEB that matches the performance of larger models. Extensive experiments demonstrate that our proposal performs favorably against the state-of-the-art SR algorithms in terms of visual quality, memory footprint, and inference time.

Original languageEnglish
Pages (from-to)57383-57397
Number of pages15
JournalIEEE Access
Publication statusPublished - 2022


  • Deep learning
  • Frequency-based methods
  • Lightweight architectures
  • Single image super-resolution


Dive into the research topics of 'Frequency-Based Enhancement Network for Efficient Super-Resolution'. Together they form a unique fingerprint.

Cite this