Unsupervised Image Fusion Using Deep Image Priors

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

2 Citations (Scopus)
18 Downloads (Pure)


A significant number of researchers have applied deep learning methods to image fusion. However, most works require a large amount of training data or depend on pre-trained models or frameworks to capture features from source images. This is inevitably hampered by a shortage of training data or a mismatch between the framework and the actual problem. Deep Image Prior (DIP) has been introduced to exploit convolutional neural networks' ability to synthesize the 'prior' in the input image. However, the original design of DIP is hard to be generalized to multi-image processing problems, particularly for image fusion. Therefore, we propose a new image fusion technique that extends DIP to fusion tasks formulated as inverse problems. Additionally, we apply a multi-channel approach to enhance DIP's effect further. The evaluation is conducted with several commonly used image fusion assessment metrics. The results are compared with state-of-the-art image fusion methods. Our method outperforms these techniques for a range of metrics. In particular, it is shown to provide the best objective results for most metrics when applied to medical images.
Original languageEnglish
Title of host publicationUnsupervised Image Fusion Using Deep Image Priors
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)978-1-6654-9620-9
ISBN (Print)978-1-6654-9621-6
Publication statusPublished - 18 Oct 2022

Bibliographical note

2022 IEEE International Conference on Image Processing (ICIP)


  • cs.CV


Dive into the research topics of 'Unsupervised Image Fusion Using Deep Image Priors'. Together they form a unique fingerprint.

Cite this