A Generative Model Method for Unsupervised Multispectral Image Fusion in Remote Sensing

TL;DR

This paper introduces a novel unsupervised generative model for multispectral image fusion in remote sensing, effectively balancing spectral and spatial fidelity through a multi-objective loss function and discriminator design.

Contribution

The work presents a new unsupervised generative approach with dual discriminators for spectral and spatial distortion minimization, outperforming recent methods.

Findings

Superior performance on multiple datasets and metrics

Effective reduction of spectral and spatial distortions

Outperforms recent state-of-the-art methods

Abstract

This paper presents a generative model method for multispectral image fusion in remote sensing which is trained without supervision. This method eases the supervision of learning and it also considers a multi-objective loss function to achieve image fusion. The loss function incorporates both spectral and spatial distortions. Two discriminators are designed to minimize the spectral and spatial distortions of the generative output. Extensive experimentations are conducted using three public domain datasets. The comparison results across four reduced-resolution and three full-resolution objective metrics show the superiority of the developed method over several recently developed methods.