J Shanghai Jiaotong Univ Sci ›› 2023, Vol. 28 ›› Issue (6): 793-801.doi: 10.1007/s12204-022-2453-2

• • 上一篇    下一篇



  1. (北京理工大学 信息与电子学院,北京 100081)
  • 接受日期:2021-03-29 出版日期:2023-11-28 发布日期:2023-12-04

Stagewise Training for Hybrid-Distorted Image Restoration

HOU Shujuan* (侯舒娟),ZHU Wenping (朱文萍),LI Hai (李海)   

  1. (School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China)
  • Accepted:2021-03-29 Online:2023-11-28 Published:2023-12-04

摘要: 图像复原是将退化图像恢复至接近理想图像的过程。以前的研究大多集中在单一失真图像上,然而大多数真实图像都经历了多种失真,单一失真图像复原算法无法有效提高图像质量。此外,现有的几种混合失真图像复原算法不具备处理单一失真的兼容性。因此,本文提出了一种基于分阶段训练的端到端神经网络。具体来说,该网络选择了三个典型的图像复原任务:图像去噪、图像修复和图像超分辨率。整个训练过程分为单一失真训练、两种类型的混合失真训练和三种类型的混合失真训练。损失函数的设计是基于深度监督的思想。实验结果表明,该方法不仅在混合失真图像复原方面优于其他方法,而且适用于单一失真图像复原。

关键词: 图像复原,分阶段训练,混合失真,单一失真

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.

Key words: image restoration, stagewise training, hybrid distortion, single distortion