🤖 AI Summary
To address high-frequency detail distortion, insufficient texture realism, and underutilized efficiency of Transformer architectures in real-world image super-resolution, this paper proposes GAN-CFAT—a novel framework integrating Generative Adversarial Networks (GANs) with a Composite Fusion Attention Transformer (CFAT). Key contributions include: (i) the first incorporation of CFAT into the GAN generator to enhance hierarchical feature modeling; (ii) a semantic-aware discriminator that enforces structural consistency; (iii) adaptive degradation modeling to improve robustness against diverse real-world degradations; and (iv) a wavelet-domain joint loss function to strengthen high-frequency fidelity. Extensive experiments on multiple real-world degradation benchmarks demonstrate that GAN-CFAT consistently surpasses state-of-the-art methods in both quantitative metrics (e.g., PSNR, SSIM) and perceptual quality, achieving significant improvements in fine-detail recovery and texture realism.
📝 Abstract
In the field of single image super-resolution (SISR), transformer-based models, have demonstrated significant advancements. However, the potential and efficiency of these models in applied fields such as real-world image super-resolution have been less noticed and there are substantial opportunities for improvement. Recently, composite fusion attention transformer (CFAT), outperformed previous state-of-the-art (SOTA) models in classic image super-resolution. In this paper, we propose a novel GAN-based framework by incorporating the CFAT model to effectively exploit the performance of transformers in real-world image super-resolution. In our proposed approach, we integrate a semantic-aware discriminator to reconstruct fine details more accurately and employ an adaptive degradation model to better simulate real-world degradations. Moreover, we introduce a new combination of loss functions by adding wavelet loss to loss functions of GAN-based models to better recover high-frequency details. Empirical results demonstrate that IG-CFAT significantly outperforms existing SOTA models in both quantitative and qualitative metrics. Our proposed model revolutionizes the field of real-world image super-resolution and demonstrates substantially better performance in recovering fine details and generating realistic textures. The introduction of IG-CFAT offers a robust and adaptable solution for real-world image super-resolution tasks.