Real-time Blind Deblurring Based on Lightweight Deep-Wiener-Network

TL;DR

This paper introduces a lightweight deep-wiener-network for real-time blind image deblurring, achieving high speed and efficiency suitable for practical applications.

Contribution

It proposes a novel lightweight deep-wiener-network architecture that significantly improves inference speed and reduces parameters for blind deblurring.

Findings

Achieves 100 images/sec processing speed

Outperforms state-of-the-art in inference time and model size

Effective for real-time blind deblurring applications

Abstract

In this paper, we address the problem of blind deblurring with high efficiency. We propose a set of lightweight deep-wiener-network to finish the task with real-time speed. The Network contains a deep neural network for estimating parameters of wiener networks and a wiener network for deblurring. Experimental evaluations show that our approaches have an edge on State of the Art in terms of inference times and numbers of parameters. Two of our models can reach a speed of 100 images per second, which is qualified for real-time deblurring. Further research may focus on some real-world applications of deblurring with our models.