Block-Attentive Subpixel Prediction Networks for Computationally Efficient Image Restoration

Taeoh Kim, Chajin Shin, Sangjin Lee, Sangyoun Lee

Research output: Contribution to journalArticlepeer-review


Image restoration based on the Deep Convolutional Neural Network (CNN) based image restoration has demonstrated promising results in many sub-tasks, such as image super-resolution, compression artifacts removal, image denoising, and image enhancement. Compared to many CNN-based high-level vision tasks that predict sparse probabilities of each class, the CNN for image restoration requires dense pixel-level predictions with precise intensity-level values. Therefore, a minimum number of spatial pooling (or down-sampling) operations is required to maintain the image details. Therefore, designing a fast or lightweight model for image restoration is a difficult problem and is even more critical when the spatial resolution of an image becomes larger. In this paper, we propose a family of networks called Subpixel Prediction Networks (SPNs) that predict reshaped and spatially down-sampled block-wise tensors instead of raw images with full resolution. Under this scheme, spatial downsampling decreases the restoration performance less while making the network faster. We propose a novel Subpixel Block Attention (SBA) module that re-calibrates blockwise features to diminish blockwise discontinuity to increase the performance further. The experimental results reveal that these networks demonstrate good trade-offs between speed (number of computations) and restoration performance in the three image restoration tasks: image compression artifacts removal, color image denoising, and image enhancement.

Original languageEnglish
Article number9464349
Pages (from-to)90881-90895
Number of pages15
JournalIEEE Access
Publication statusPublished - 2021

Bibliographical note

Funding Information:
This work was supported by the Institute of Information and communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government [(Ministry of Science and Information and Communications Technology (ICT)) (MSIT)], The development of human Re-identification and masked face recognition based on CCTV camera, under Grant 2021-0-00172.

Publisher Copyright:
© 2013 IEEE.

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)
  • Electrical and Electronic Engineering


Dive into the research topics of 'Block-Attentive Subpixel Prediction Networks for Computationally Efficient Image Restoration'. Together they form a unique fingerprint.

Cite this