Learned Edge-Guided Multiple Attention-based Generative Adversarial Network for Single Image Super-Resolution
Year: 2025
Type: article
Abstract: - It is well-known that recovering high-frequency details from low-resolution images remains a major challengein single image super-resolution. This work presents a multiple attention-based generative adversarial network thatleverages a learned edge detector to enhance structural details in the reconstructed images. A multiple attention-basedblock is designed to capture multi-level contextual information and different attention-based features. In addition, aScale-Invariant Feature Transform-based loss function is employed to ensure the preservation of scale-invariant featuresand reducing discrepancies between the generated and ground-truth images. Comprehensive experiments on standarddatasets demonstrate that the proposed approach consistently outperforms existing state-of-the-art models and achieveshigher PSNR and SSIM values while delivering perceptually superior results with lower LPIPS scores.
Institution: National Institute of Technology Kurukshetra
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7092308859
FWCI:
Cites:
Cited by:
Related to: