IVCVAug 5, 2022

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

arXiv:2208.03324v224 citationsh-index: 37Has Code
AI Analysis

This addresses the problem of balancing objective and perceptual quality in image super-resolution for applications like media enhancement, though it is incremental as it builds on existing trade-off concepts.

The paper tackles the perception-distortion trade-off in single-image super-resolution by proposing a low-frequency constrained model (LFc-SR) that balances pixel accuracy and perceptual quality in a single model, achieving state-of-the-art performance with high PSNR and perceptual scores without post-processing.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes