mlsanityData to 14 Oct 2026

ISTA-Inspired Network for Image Super-Resolution

arXiv 2210.07818 ↗First posted 14 Oct 2022eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning for image super-resolution (SR) has been investigated by numerous researchers in recent years. Most of the works concentrate on effective block designs and improve the network representation but lack interpretation. There are also iterative optimization-inspired networks for image SR, which take the solution step as a whole without giving an explicit optimization step. This paper proposes an unfolding iterative shrinkage thresholding algorithm (ISTA) inspired network for interpretable image SR. Specifically, we analyze the problem of image SR and propose a solution based on the ISTA method. Inspired by the mathematical analysis, the ISTA block is developed to conduct the optimization in an end-to-end manner. To make the exploration more effective, a multi-scale exploitation block and multi-scale attention mechanism are devised to build the ISTA block. Experimental results show the proposed ISTA-inspired restoration network (ISTAR) achieves competitive or better performances than other optimization-inspired works with fewer parameters and lower computation complexity.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 57 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

26 of 57 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  9. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  10. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  11. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
  12. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 329
14 more
  1. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  2. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 264
  3. 2020Deep Unfolding Network for Image Super-Resolutioncited by 254
  4. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 246
  5. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  6. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227
  7. 2018Residual Dense Network for Image Restorationcited by 181
  8. 2020Residual Feature Distillation Network for Lightweight Image Super-Resolutioncited by 122
  9. 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
  10. 2016Deep Edge Guided Recurrent Residual Learning for Image Super-Resolutioncited by 22
  11. 2020Iterative Network for Image Super-Resolutioncited by 11
  12. 2022Cross-SRN: Structure-Preserving Super-Resolution Network with Cross Convolutioncited by 10
  13. 2020Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolutioncited by 1
  14. 2022Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolutioncited by 1

Built on by

Not cited yet.