@Article{ArminMehri2023,
author="Armin Mehri
and Parichehr Behjati
and Angel Sappa",
title="TnTViT-G: Transformer in Transformer Network for Guidance Super Resolution",
journal="IEEE Access",
year="2023",
volume="11",
pages="11529--11540",
abstract="Image Super Resolution is a potential approach that can improve the image quality of low-resolution optical sensors, leading to improved performance in various industrial applications. It is important to emphasize that most state-of-the-art super resolution algorithms often use a single channel of input data for training and inference. However, this practice ignores the fact that the cost of acquiring high-resolution images in various spectral domains can differ a lot from one another. In this paper, we attempt to exploit complementary information from a low-cost channel (visible image) to increase the image quality of an expensive channel (infrared image). We propose a dual stream Transformer-based super resolution approach that uses the visible image as a guide to super-resolve another spectral band image. To this end, we introduce Transformer in Transformer network for Guidance super resolution, named TnTViT-G, an efficient and effective method that extracts the features of input images via different streams and fuses them together at various stages. In addition, unlike other guidance super resolution approaches, TnTViT-G is not limited to a fixed upsample size and it can generate super-resolved images of any size. Extensive experiments on various datasets show that the proposed model outperforms other state-of-the-art super resolution approaches. TnTViT-G surpasses state-of-the-art methods by up to 0.19\~{}2.3dB , while it is memory efficient.",
optnote="MSIAU",
optnote="exported from refbase (http://158.109.8.37/show.php?record=3876), last updated on Fri, 12 Jan 2024 10:47:46 +0100",
opturl="https://ieeexplore.ieee.org/document/10035402"
}