Stagewise Training for Hybrid-Distorted Image Restoration

Shujuan Hou*, Wenping Zhu, Hai Li

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Image restoration is the problem of restoring a real degraded image. Previous studies mostly focused on single distortion. However, most of the real images experience multiple distortions, and single distortion image restoration algorithms can not effectively improve the image quality. Moreover, few existing hybrid distortion image restoration algorithms can not deal with single distortion. Therefore, an end-to-end pipeline network based on stagewise training is proposed in this paper. Specifically, the network selects three typical image restoration tasks: denoising, inpainting, and super resolution. The whole training process is divided into single distortion training, hybrid distortion training of two types, and hybrid distortion training of three types. The design of loss function draws on the idea of deep supervision. Experimental results prove that the proposed method is not only superior to other methods in hybrid-distorted image restoration, but also suitable for single distortion image restoration.

Translated title of the contribution混合失真图像复原的分阶段训练
Original languageEnglish
Pages (from-to)793-801
Number of pages9
JournalJournal of Shanghai Jiaotong University (Science)
Volume28
Issue number6
DOIs
Publication statusPublished - Dec 2023

Keywords

  • A
  • TP 391.9
  • hybrid distortion
  • image restoration
  • single distortion
  • stagewise training

Fingerprint

Dive into the research topics of 'Stagewise Training for Hybrid-Distorted Image Restoration'. Together they form a unique fingerprint.

Cite this

Hou, S., Zhu, W., & Li, H. (2023). Stagewise Training for Hybrid-Distorted Image Restoration. Journal of Shanghai Jiaotong University (Science), 28(6), 793-801. https://doi.org/10.1007/s12204-022-2453-2