DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks

TL;DR

DSRGAN introduces a novel detail prior to enhance perceptual single image super-resolution, effectively restoring realistic high-frequency details by combining traditional algorithms with deep learning, outperforming existing methods in perceptual quality.

Contribution

The paper proposes DSRGAN, a new GAN-based super-resolution model that incorporates a detail prior and dual discriminators to improve high-frequency detail restoration.

Findings

Outperforms state-of-the-art SISR methods on perceptual metrics.

Achieves comparable results to top methods on fidelity metrics.

Demonstrates the effectiveness of integrating conventional algorithms into deep learning.

Abstract

The generative adversarial network (GAN) is successfully applied to study the perceptual single image superresolution (SISR). However, the GAN often tends to generate images with high frequency details being inconsistent with the real ones. Inspired by conventional detail enhancement algorithms, we propose a novel prior knowledge, the detail prior, to assist the GAN in alleviating this problem and restoring more realistic details. The proposed method, named DSRGAN, includes a well designed detail extraction algorithm to capture the most important high frequency information from images. Then, two discriminators are utilized for supervision on image-domain and detail-domain restorations, respectively. The DSRGAN merges the restored detail into the final output via a detail enhancement manner. The special design of DSRGAN takes advantages from both the model-based conventional algorithm and the data-driven deep learning network. Experimental results demonstrate that the DSRGAN outperforms the state-of-the-art SISR methods on perceptual metrics and achieves comparable results in terms of fidelity metrics simultaneously. Following the DSRGAN, it is feasible to incorporate other conventional image processing algorithms into a deep learning network to form a model-based deep SISR.