Blind Motion Deblurring through SinGAN Architecture
This work addresses the problem of blind motion deblurring for image processing researchers, specifically exploring a data-efficient approach using a single-image generative model, which is an incremental step in applying existing architectures to new tasks.
This paper explores the use of SinGAN architecture for blind motion deblurring, aiming to reconstruct sharp images from blurry observations. The authors investigate if SinGAN, which learns from a single natural image and captures internal patch distributions, can be applied to this ill-posed image restoration problem.
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.