Blind Motion Deblurring through SinGAN Architecture

TL;DR

This paper explores using SinGAN, a single-image generative model, for blind motion deblurring, aiming to address the data-hungry nature of traditional methods and improve restoration quality.

Contribution

It introduces a novel approach applying SinGAN architecture to blind motion deblurring, leveraging its internal patch distribution for image restoration.

Findings

SinGAN can effectively restore sharp images from blurry inputs.

The method reduces the need for large training datasets.

Results show promising quality in deblurring tasks.

Abstract

Blind motion deblurring involves reconstructing a sharp image from an observation that is blurry. It is a problem that is ill-posed and lies in the categories of image restoration problems. The training data-based methods for image deblurring mostly involve training models that take a lot of time. These models are data-hungry i.e., they require a lot of training data to generate satisfactory results. Recently, there are various image feature learning methods developed which relieve us of the need for training data and perform image restoration and image synthesis, e.g., DIP, InGAN, and SinGAN. SinGAN is a generative model that is unconditional and could be learned from a single natural image. This model primarily captures the internal distribution of the patches which are present in the image and is capable of generating samples of varied diversity while preserving the visual content of the image. Images generated from the model are very much like real natural images. In this paper, we focus on blind motion deblurring through SinGAN architecture.