Super-Resolved Image Perceptual Quality Improvement via Multi-Feature Discriminators

TL;DR

This paper introduces a multi-feature discriminator GAN framework for image super-resolution that improves perceptual quality by accurately discriminating features and enhancing salient regions, outperforming existing methods in visual quality.

Contribution

The paper proposes a novel GAN-based SR framework with multiple discriminators and weighted content loss, enhancing perceptual quality and salient region restoration over prior single-discriminator methods.

Findings

Improved perceptual quality and visual perception in SR images.

Achieved competitive PI and NIQE metrics compared to state-of-the-art.

Enhanced salient regions and textures in super-resolved images.

Abstract

Generative adversarial network (GAN) for image super-resolution (SR) has attracted enormous interests in recent years. However, the GAN-based SR methods only use image discriminator to distinguish SR images and high-resolution (HR) images. Image discriminator fails to discriminate images accurately since image features cannot be fully expressed. In this paper, we design a new GAN-based SR framework GAN-IMC which includes generator, image discriminator, morphological component discriminator and color discriminator. The combination of multiple feature discriminators improves the accuracy of image discrimination. Adversarial training between the generator and multi-feature discriminators forces SR images to converge with HR images in terms of data and features distribution. Moreover, in some cases, feature enhancement of salient regions is also worth considering. GAN-IMC is further optimized by weighted content loss (GAN-IMCW), which effectively restores and enhances salient regions in SR images. The effectiveness and robustness of our method are confirmed by extensive experiments on public datasets. Compared with state-of-the-art methods, the proposed method not only achieves competitive Perceptual Index (PI) and Natural Image Quality Evaluator (NIQE) values but also obtains pleasant visual perception in image edge, texture, color and salient regions.