HSR-KAN: Efficient Hyperspectral Image Super-Resolution via Kolmogorov-Arnold Networks

📅 2024-08-24
🏛️ arXiv.org
📈 Citations: 1
Influential: 0
📄 PDF

career value

177K/year
🤖 AI Summary
This paper addresses the hyperspectral super-resolution task of fusing a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) to reconstruct a high-resolution hyperspectral image (HR-HSI). We propose a novel method based on the Kolmogorov–Arnold Network (KAN). Our key contributions are: (1) the KAN-Fusion module, the first to enable joint spectral–spatial cross-modal modeling; and (2) the KAN Channel Attention Block (KAN-CAB), which replaces conventional MLPs with learnable KANs to enhance spectral representation fidelity while mitigating the curse of dimensionality. Extensive experiments on multiple benchmark datasets demonstrate state-of-the-art performance, with significant improvements in PSNR and SSIM over existing methods. The source code is publicly available.

Technology Category

Application Category

📝 Abstract
Hyperspectral images (HSIs) have great potential in various visual tasks due to their rich spectral information. However, obtaining high-resolution hyperspectral images remains challenging due to limitations of physical imaging. Inspired by Kolmogorov-Arnold Networks (KANs), we propose an efficient HSI super-resolution (HSI-SR) model to fuse a low-resolution HSI (LR-HSI) and a high-resolution multispectral image (HR-MSI), yielding a high-resolution HSI (HR-HSI). To achieve the effective integration of spatial information from HR-MSI, we design a fusion module based on KANs, called KAN-Fusion. Further inspired by the channel attention mechanism, we design a spectral channel attention module called KAN Channel Attention Block (KAN-CAB) for post-fusion feature extraction. As a channel attention module integrated with KANs, KAN-CAB not only enhances the fine-grained adjustment ability of deep networks, enabling networks to accurately simulate details of spectral sequences and spatial textures, but also effectively avoid Curse of Dimensionality. Extensive experiments show that, compared to current state-of-the-art HSI-SR methods, proposed HSR-KAN achieves the best performance in terms of both qualitative and quantitative assessments. Our code is available at: https://github.com/Baisonm-Li/HSR-KAN.
Problem

Research questions and friction points this paper is trying to address.

Fusing low-resolution hyperspectral and high-resolution multispectral images
Enhancing spatial and spectral details via KAN-based modules
Overcoming dimensionality curse in hyperspectral super-resolution
Innovation

Methods, ideas, or system contributions that make the work stand out.

Uses KAN-Fusion for spatial information integration
Implements KAN-CAB for spectral channel attention
Avoids Curse of Dimensionality effectively
🔎 Similar Papers
No similar papers found.
B
Baisong Li
College of Computer Science and Technology, Jilin University; Key Laboratory of Symbolic Computation and Krowledge Engineering of Ministry of Education, Jilin University
X
Xingwang Wang
College of Computer Science and Technology, Jilin University; Key Laboratory of Symbolic Computation and Krowledge Engineering of Ministry of Education, Jilin University
H
Haixiao Xu
College of Computer Science and Technology, Jilin University; Key Laboratory of Symbolic Computation and Krowledge Engineering of Ministry of Education, Jilin University