Defocus Deblur Microscopy via Head-to-Tail Cross-scale Fusion

TL;DR

This paper introduces a novel microscopy defocus deblurring method using a head-to-tail cross-scale fusion in a multi-scale U-Net, improving feature learning and outperforming existing models.

Contribution

It proposes a non-cascade residual multi-scale U-Net with head-to-tail feature fusion for more accurate microscopy defocus deblurring.

Findings

Better deblurring performance than existing models

Effective cross-scale feature fusion improves learning

Applicable to microscopy imaging with axial drift issues

Abstract

Microscopy imaging is vital in biology research and diagnosis. When imaging at the scale of cell or molecule level, mechanical drift on the axial axis can be difficult to correct. Although multi-scale networks have been developed for deblurring, those cascade residual learning approaches fail to accurately capture the end-to-end non-linearity of deconvolution, a relation between in-focus images and their out-of-focus counterparts in microscopy. In our model, we adopt a structure of multi-scale U-Net without cascade residual leaning. Additionally, in contrast to the conventional coarse-to-fine model, our model strengthens the cross-scale interaction by fusing the features from the coarser sub-networks with the finer ones in a head-to-tail manner: the decoder from the coarser scale is fused with the encoder of the finer ones. Such interaction contributes to better feature learning as fusion happens across decoder and encoder at all scales. Numerous experiments demonstrate that our method yields better performance when compared with other existing models.