Guided Deep Decoder: Unsupervised Image Pair Fusion

TL;DR

This paper introduces a unified, unsupervised deep learning framework for image pair fusion that leverages a guided deep decoder network, achieving state-of-the-art results across different fusion tasks without requiring training data.

Contribution

It proposes a general, unsupervised guided deep decoder network that unifies various image fusion tasks using multi-scale guidance features, eliminating the need for task-specific priors.

Findings

Achieves state-of-the-art performance in multiple image fusion tasks.

Operates in an unsupervised manner without training data.

Unifies different fusion problems under a single framework.

Abstract

The fusion of input and guidance images that have a tradeoff in their information (e.g., hyperspectral and RGB image fusion or pansharpening) can be interpreted as one general problem. However, previous studies applied a task-specific handcrafted prior and did not address the problems with a unified approach. To address this limitation, in this study, we propose a guided deep decoder network as a general prior. The proposed network is composed of an encoder-decoder network that exploits multi-scale features of a guidance image and a deep decoder network that generates an output image. The two networks are connected by feature refinement units to embed the multi-scale features of the guidance image into the deep decoder network. The proposed network allows the network parameters to be optimized in an unsupervised way without training data. Our results show that the proposed network can achieve state-of-the-art performance in various image fusion problems.