PAKAN: Pixel Adaptive Kolmogorov-Arnold Network Modules for Pansharpening

TL;DR

This paper introduces PAKAN, a novel neural network module with pixel-adaptive activation functions for improved pansharpening, demonstrating significant performance gains over traditional static-activation models.

Contribution

The paper proposes a new pixel-adaptive Kolmogorov-Arnold Network framework with adaptive variants that enhance spectral-spatial fusion in pansharpening tasks.

Findings

Significant performance improvement in pansharpening accuracy.

Adaptive modules outperform static activation function models.

Demonstrated effectiveness across extensive experiments.

Abstract

Pansharpening aims to fuse high-resolution spatial details from panchromatic images with the rich spectral information of multispectral images. Existing deep neural networks for this task typically rely on static activation functions, which limit their ability to dynamically model the complex, non-linear mappings required for optimal spatial-spectral fusion. While the recently introduced Kolmogorov-Arnold Network (KAN) utilizes learnable activation functions, traditional KANs lack dynamic adaptability during inference. To address this limitation, we propose a Pixel Adaptive Kolmogorov-Arnold Network framework. Starting from KAN, we design two adaptive variants: a 2D Adaptive KAN that generates spline summation weights across spatial dimensions and a 1D Adaptive KAN that generates them across spectral channels. These two components are then assembled into PAKAN 2to1 for feature fusion and PAKAN 1to1 for feature refinement. Extensive experiments demonstrate that our proposed modules significantly enhance network performance, proving the effectiveness and superiority of pixel-adaptive activation in pansharpening tasks.