Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution

TL;DR

This paper introduces a novel single-image super-resolution model that balances pixel accuracy and perceptual quality using a low-frequency constraint and ADMM optimization, achieving state-of-the-art results without post-processing.

Contribution

It proposes a new super-resolution model with a low-frequency constraint and an ADMM-based training method to balance perception and distortion in a single model.

Findings

Achieved state-of-the-art performance in super-resolution tasks.

Balanced perceptual quality and pixel accuracy without post-processing.

Demonstrated effectiveness of ADMM-based optimization in constrained learning.

Abstract

In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that successfully balance the trade-off rely on fusing results from separately trained models with ad-hoc post-processing. In this paper, we propose a novel super-resolution model with a low-frequency constraint (LFc-SR), which balances the objective and perceptual quality through a single model and yields super-resolved images with high PSNR and perceptual scores. We further introduce an ADMM-based alternating optimization method for the non-trivial learning of the constrained model. Experiments showed that our method, without cumbersome post-processing procedures, achieved the state-of-the-art performance. The code is available at https://github.com/Yuehan717/PDASR.