WaveFuse: A Unified Unsupervised Framework for Image Fusion with Discrete Wavelet Transform

Shaolei Liu, Manning Wang^†, Zhijian Song^†

The 28th International Conference on Neural Information Processing (ICONIP2021)

Abstract

We propose an unsupervised image fusion architecture for multiple application scenarios based on the combination of multi-scale discrete wavelet transform through regional energy and deep learning. To our best knowledge, this is the first time that a conventional image fusion method has been combined with deep learning for feature maps fusion. The useful information of feature maps can be utilized adequately through multi-scale discrete wavelet transform in our proposed method. Compared with other state-of-the-art fusion methods, the proposed algorithm exhibits better fusion  performance in both subjective and objective evaluation. Moreover, it's worth mentioning that comparable fusion performance trained in COCO dataset can be obtained by training with a much smaller dataset with only hundreds of images chosen randomly from COCO. Hence, the training time is shortened substantially, leading to the improvement of the model's performance both in practicality and training efficiency.

Paper Link: https://link.springer.com/chapter/10.1007/978-3-030-92273-3_14

Code Link:https://github.com/slliuEric/WaveFuse_code