Deep Fusion Prior for Plenoptic Super-Resolution All-in-Focus Imaging

TL;DR

This paper introduces a novel dataset-free unsupervised deep learning framework called Deep Fusion Prior (DFP) that simultaneously performs multi-focus image fusion and super-resolution, outperforming existing separate methods.

Contribution

It unifies multi-focus image fusion and super-resolution into a single physical framework and proposes the first dataset-free unsupervised method for this combined task.

Findings

DFP outperforms state-of-the-art methods in MFIF and SR.

First dataset-free unsupervised approach for combined MFIF and SR.

Framework is flexible and can be improved with updated networks and focus measurement tactics.

Abstract

Multi-focus image fusion (MFIF) and super-resolution (SR) are the inverse problem of imaging model, purposes of MFIF and SR are obtaining all-in-focus and high-resolution 2D mapping of targets. Though various MFIF and SR methods have been designed; almost all the them deal with MFIF and SR separately. This paper unifies MFIF and SR problems in the physical perspective as the multi-focus image super resolution fusion (MFISRF), and we propose a novel unified dataset-free unsupervised framework named deep fusion prior (DFP) based-on deep image prior (DIP) to address such MFISRF with single model. Experiments have proved that our proposed DFP approaches or even outperforms those state-of-art MFIF and SR method combinations. To our best knowledge, our proposed work is a dataset-free unsupervised method to simultaneously implement the multi-focus fusion and super-resolution task for the first time. Additionally, DFP is a general framework, thus its networks and focus measurement tactics can be continuously updated to further improve the MFISRF performance. DFP codes are open source available at http://github.com/GuYuanjie/DeepFusionPrior.