ShiVaNet: Shift Variant Image Deconvolution using Deep Learning

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 optical system’s point spread function depends on the position of the object point from the principal axis. For example, asymmetrical lenses can cause space variant aberration.In this paper, we first simulate our space-variant aberrations by generating PSFs using the 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 block as described in [1] by introducing Simplified Channel Attention and Transpose Attention to improve the performance of the module. We also devise a novel UNet refinement block by fusing a ConvNext-V2 block with Channel Attention and coupling with Transposed Attention [2]. Our model performs better than state-of-the-art restoration models by a factor of 0.2 dB.