Imaging Science MS Defense: Arnab Ghosh
MS Thesis Defense
ShiVaNet: Shift Variant Deconvolution Using Deep Learning
Imaging Science MS Candidate
Chester F. Carlson Center for Imaging Science, RIT
Register Here for Zoom Link
Image Deconvolution is a well-studied problem that seeks to restore the original sharp image from a blurry image formed in the imaging system. The Point Spread function (PSF) of a particular system can be used to infer the original sharp image given the blurred image. However, such a problem is usually simplified by making the shift invariant assumption over the field of view (FOV). Realistic systems are shift-variant; the point spread function of the optical system is dependent on the position of object point from the principal axis. For example, asymmetrical lenses can cause space variant aberration. We first simulate our space-variant aberrations by generating PSFs using Seidel Aberration polynomial and use a space variant forward blur model to generate our shift variant blurred image pairs. We then introduce, ShiVaNet. It is a two-stage architecture that builds upon the Learnable Wiener Deconvolution concept by introducing Simplified Channel Attention and Transpose Attention to improve the performance of the module. We also device a novel UNet refinement block by fusing a ConvNext-V2 block with Channel Attention and couple with Transposed Attention. Our model performs better than state-of-the-art restoration models by a factor of 0.2dB.
Undergraduates, graduates, and experts. Those with interest in the topic.
To request an interpreter, please visit https://myaccess.rit.edu
When and Where
Open to the Public