GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention

TL;DR

This paper introduces GDCA, a GAN-based method for single image super-resolution that uses dual discriminators and channel attention to produce sharper, more visually appealing images than traditional approaches.

Contribution

The paper proposes a novel GAN architecture with dual discriminators and channel attention for improved image super-resolution performance.

Findings

GDCA generates sharper, more pleasing images.

Outperforms conventional super-resolution methods.

Experimental results validate effectiveness.

Abstract

Single Image Super-Resolution (SISR) is a very active research field. This paper addresses SISR by using a GAN-based approach with dual discriminators and incorporating it with an attention mechanism. The experimental results show that GDCA can generate sharper and high pleasing images compare to other conventional methods.