SWViT-RRDB: Shifted Window Vision Transformer Integrating Residual in Residual Dense Block for Remote Sensing Super-Resolution

Mohamed Ramzy Ibrahim*, Roberto Benavente Vidal, Daniel Ponsa Mussarra, Felipe Lumbreras Ruiz

*Autor correspondiente de este trabajo

Producción científica: Capítulo del libroCapítuloInvestigaciónrevisión exhaustiva

1 Cita (Scopus)

Resumen

Remote sensing applications, impacted by acquisition season and sensor variety, require high-resolution images. Transformer-based models improve satellite image super-resolution but are less effective than convolutional neural networks (CNNs) at extracting local details, crucial for image clarity. This paper introduces SWViT-RRDB, a new deep learning model for satellite imagery super-resolution. The SWViT-RRDB, combining transformer with convolution and attention blocks, overcomes the limitations of existing models by better representing small objects in satellite images. In this model, a pipeline of residual fusion group (RFG) blocks is used to combine the multi-headed self-attention (MSA) with residual in residual dense block (RRDB). This combines global and local image data for better super-resolution. Additionally, an overlapping cross-attention block (OCAB) is used to enhance fusion and allow interaction between neighboring pixels to maintain long-range pixel dependencies across the image. The SWViT-RRDB model and its larger variants outperform state-of-the-art (SoTA) models on two different satellite datasets in terms of PSNR and SSIM
Idioma originalInglés
Título de la publicación alojada19th International Conference on Computer Vision Theory ad Applications (VISAPP'2024))
Páginas575-582
Número de páginas8
Volumen3
ISBN (versión digital)978-989-758-679-8
DOI
EstadoPublicada - 1 ene 2024

Serie de la publicación

NombreProceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Huella

Profundice en los temas de investigación de 'SWViT-RRDB: Shifted Window Vision Transformer Integrating Residual in Residual Dense Block for Remote Sensing Super-Resolution'. En conjunto forman una huella única.

Citar esto