Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective

Lingchen Sun

doi:10.1109/TIP.2024.3434426

Return

Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective

2024-01-01

DOI：10.1109/TIP.2024.3434426

Original

Original request for help

Save

Abstract

En 中文

High perceptual quality and low distortion degree are two important goals in image restoration tasks such as super-resolution (SR). Most of the existing SR methods aim to achieve these goals by minimizing the corresponding yet conflicting losses, such as the & ell;(1) loss and the adversarial loss. Unfortunately, the commonly used gradient-based optimizers, such as Adam, are hard to balance these objectives due to the opposite gradient decent directions of the contradictory losses. In this paper, we formulate the perception-distortion trade-off in SR as a multi-objective optimization problem and develop a new optimizer by integrating the gradient-free evolutionary algorithm (EA) with gradient-based Adam, where EA and Adam focus on the divergence and convergence of the optimization directions respectively. As a result, a population of optimal models with different perception-distortion preferences is obtained. We then design a fusion network to merge these models into a single stronger one for an effective perception-distortion trade-off. Experiments demonstrate that with the same backbone network, the perception-distortion balanced SR model trained by our method can achieve better perceptual quality than its competitors while attaining better reconstruction fidelity. Codes and models can be found at https://github.com/csslc/EA-Adam .

Keywords:

Optimization

Indexes

Distortion

Loss measurement

Task analysis

Evolutionary computation

Distortion measurement

Super-resolution

GAN

evolutionary algorithm

optimization