WaveFuse: A Unified Deep Framework for Image Fusion with Discrete Wavelet Transform
This work addresses image fusion for applications like computer vision, offering a more efficient training approach, though it appears incremental as it builds on existing methods.
The authors tackled the problem of image fusion across multiple applications by combining multi-scale discrete wavelet transform with deep learning in an unsupervised framework, achieving better fusion performance than state-of-the-art methods in subjective and objective evaluations and reducing training time by using a much smaller dataset (hundreds of images) to achieve comparable results.
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 the conventional image fusion method has been combined with deep learning. 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 method, 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.