CVDec 2, 2021

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

arXiv:2112.01030v3188 citations
Originality Incremental advance
AI Analysis

This work addresses image fusion for applications like photography and computer vision, but it is incremental as it builds on existing transformer and self-supervised learning approaches.

The paper tackled the problem of multi-exposure image fusion by proposing TransMEF, a transformer-based framework using self-supervised multi-task learning, which achieved the best performance compared to 11 other methods on a benchmark dataset in both subjective and objective evaluations.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes