LKFormer: Large Kernel Transformer for Infrared Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qin, Feiwei, Yan, Kang, Wang, Changmiao, Ge, Ruiquan, Peng, Yong, Zhang, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914651149697024
author Qin, Feiwei
Yan, Kang
Wang, Changmiao
Ge, Ruiquan
Peng, Yong
Zhang, Kai
author_facet Qin, Feiwei
Yan, Kang
Wang, Changmiao
Ge, Ruiquan
Peng, Yong
Zhang, Kai
contents Given the broad application of infrared technology across diverse fields, there is an increasing emphasis on investigating super-resolution techniques for infrared images within the realm of deep learning. Despite the impressive results of current Transformer-based methods in image super-resolution tasks, their reliance on the self-attentive mechanism intrinsic to the Transformer architecture results in images being treated as one-dimensional sequences, thereby neglecting their inherent two-dimensional structure. Moreover, infrared images 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 Kernel Transformer (LKFormer), to address this issue. Specifically, we have designed a Large Kernel Residual Attention (LKRA) module with linear complexity. This mainly employs depth-wise convolution with large kernels to execute non-local feature modeling, thereby substituting the standard self-attentive layer. Additionally, we have devised a novel feed-forward network structure called Gated-Pixel Feed-Forward Network (GPFN) to augment the LKFormer's capacity to manage the information flow within the network. Comprehensive experimental results reveal that our method surpasses the most advanced techniques available, using fewer parameters and yielding considerably superior performance.The source code will be available at https://github.com/sad192/large-kernel-Transformer.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11859
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LKFormer: Large Kernel Transformer for Infrared Image Super-Resolution
Qin, Feiwei
Yan, Kang
Wang, Changmiao
Ge, Ruiquan
Peng, Yong
Zhang, Kai
Image and Video Processing
Computer Vision and Pattern Recognition
Given the broad application of infrared technology across diverse fields, there is an increasing emphasis on investigating super-resolution techniques for infrared images within the realm of deep learning. Despite the impressive results of current Transformer-based methods in image super-resolution tasks, their reliance on the self-attentive mechanism intrinsic to the Transformer architecture results in images being treated as one-dimensional sequences, thereby neglecting their inherent two-dimensional structure. Moreover, infrared images 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 Kernel Transformer (LKFormer), to address this issue. Specifically, we have designed a Large Kernel Residual Attention (LKRA) module with linear complexity. This mainly employs depth-wise convolution with large kernels to execute non-local feature modeling, thereby substituting the standard self-attentive layer. Additionally, we have devised a novel feed-forward network structure called Gated-Pixel Feed-Forward Network (GPFN) to augment the LKFormer's capacity to manage the information flow within the network. Comprehensive experimental results reveal that our method surpasses the most advanced techniques available, using fewer parameters and yielding considerably superior performance.The source code will be available at https://github.com/sad192/large-kernel-Transformer.
title LKFormer: Large Kernel Transformer for Infrared Image Super-Resolution
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.11859