English

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

Image and Video Processing 2022-08-17 v2 Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.2208.03324,
  title  = {Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution},
  author = {Yuehan Zhang and Bo Ji and Jia Hao and Angela Yao},
  journal= {arXiv preprint arXiv:2208.03324},
  year   = {2022}
}
R2 v1 2026-06-25T01:31:28.038Z