@InProceedings{MohamedRamzyIbrahim2024,
author="Mohamed Ramzy Ibrahim
and Robert Benavente
and Daniel Ponsa
and Felipe Lumbreras",
title="SWViT-RRDB: Shifted Window Vision Transformer Integrating Residual in Residual Dense Block for Remote Sensing Super-Resolution",
booktitle="19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",
year="2024",
abstract="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.",
optnote="MSIAU",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=4004), last updated on Tue, 12 Mar 2024 12:28:12 +0100",
opturl="https://www.insticc.org/node/TechnicalProgram/visigrapp/2024/presentationDetails/123993"
}