Open AccessConstrained adversarial loss for generative adversarial network‐based faithful image restoration
Author(s) -
Kim DongWook,
Chung JaeRyun,
Kim Jongho,
Lee Dae Yeol,
Jeong Se Yoon,
Jung SeungWon
Publication year - 2019
Publication title -
etri journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.295
H-Index - 46
eISSN - 2233-7326
pISSN - 1225-6463
DOI - 10.4218/etrij.2018-0473
Subject(s) - image restoration , computer science , fidelity , artificial intelligence , adversarial system , high fidelity , computer vision , generative adversarial network , noise reduction , image (mathematics) , reduction (mathematics) , image quality , image processing , mathematics , engineering , telecommunications , geometry , electrical engineering
Generative adversarial networks (GAN) have been successfully used in many image restoration tasks, including image denoising, super‐resolution, and compression artifact reduction. By fully exploiting its characteristics, state‐of‐the‐art image restoration techniques can be used to generate images with photorealistic details. However, there are many applications that require faithful rather than visually appealing image reconstruction, such as medical imaging, surveillance, and video coding. We found that previous GAN‐training methods that used a loss function in the form of a weighted sum of fidelity and adversarial loss fails to reduce fidelity loss. This results in non‐negligible degradation of the objective image quality, including peak signal‐to‐noise ratio. Our approach is to alternate between fidelity and adversarial loss in a way that the minimization of adversarial loss does not deteriorate the fidelity. Experimental results on compression‐artifact reduction and super‐resolution tasks show that the proposed method can perform faithful and photorealistic image restoration.