TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning

TL;DR

TransMEF introduces a transformer-based multi-exposure image fusion framework utilizing self-supervised multi-task learning, effectively learning from large datasets without ground truth, and combining CNN and transformer modules for enhanced local and global feature extraction.

Contribution

The paper presents a novel transformer-based framework with self-supervised multi-task learning for multi-exposure image fusion, integrating CNN and transformer modules to improve feature extraction.

Findings

Achieved state-of-the-art performance on benchmark datasets.

Outperformed 11 traditional and deep learning methods.

Effective learning without ground truth images.

Abstract

In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning. The framework is based on an encoder-decoder network, which can be trained on large natural image datasets and does not require ground truth fusion images. We design three self-supervised reconstruction tasks according to the characteristics of multi-exposure images and conduct these tasks simultaneously using multi-task learning; through this process, the network can learn the characteristics of multi-exposure images and extract more generalized features. In addition, to compensate for the defect in establishing long-range dependencies in CNN-based architectures, we design an encoder that combines a CNN module with a transformer module. This combination enables the network to focus on both local and global information. We evaluated our method and compared it to 11 competitive traditional and deep learning-based methods on the latest released multi-exposure image fusion benchmark dataset, and our method achieved the best performance in both subjective and objective evaluations.