English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Given the broad application of infrared technology across diverse fields,there is an increasing emphasis on investigating super-resolution techniquesfor infrared images within the realm of deep learning. Despite the impressiveresults of current Transformer-based methods in image super-resolution tasks,their reliance on the self-attentive mechanism intrinsic to the Transformerarchitecture results in images being treated as one-dimensional sequences,thereby neglecting their inherent two-dimensional structure. Moreover, infraredimages exhibit a uniform pixel distribution and a limited gradient range,posing challenges for the model to capture effective feature information.Consequently, we suggest a potent Transformer model, termed Large KernelTransformer (LKFormer), to address this issue. Specifically, we have designed aLarge Kernel Residual Attention (LKRA) module with linear complexity. Thismainly employs depth-wise convolution with large kernels to execute non-localfeature modeling, thereby substituting the standard self-attentive layer.Additionally, we have devised a novel feed-forward network structure calledGated-Pixel Feed-Forward Network (GPFN) to augment the LKFormer's capacity tomanage the information flow within the network. Comprehensive experimentalresults reveal that our method surpasses the most advanced techniquesavailable, using fewer parameters and yielding considerably superiorperformance.The source code will be available athttps://github.com/sad192/large-kernel-Transformer.

LKFormer: Large Kernel Transformer for Infrared Image Super-Resolution