Non-uniform Motion Deblurring with Blurry Component Divided Guidance

TL;DR

This paper introduces a novel deep two-branch network with component division and orientation-based feature fusion to effectively address non-uniform motion blur in image deblurring, outperforming existing methods.

Contribution

The paper proposes a new two-branch network with component division and orientation-based feature fusion for improved non-uniform motion deblurring.

Findings

Outperforms state-of-the-art deblurring methods in qualitative and quantitative tests.

Effectively handles large and small blurry regions separately.

Demonstrates superior restoration of sharp images from complex motion blur.

Abstract

Blind image deblurring is a fundamental and challenging computer vision problem, which aims to recover both the blur kernel and the latent sharp image from only a blurry observation. Despite the superiority of deep learning methods in image deblurring have displayed, there still exists major challenge with various non-uniform motion blur. Previous methods simply take all the image features as the input to the decoder, which handles different degrees (e.g. large blur, small blur) simultaneously, leading to challenges for sharp image generation. To tackle the above problems, we present a deep two-branch network to deal with blurry images via a component divided module, which divides an image into two components based on the representation of blurry degree. Specifically, two component attentive blocks are employed to learn attention maps to exploit useful deblurring feature representations on both large and small blurry regions. Then, the blur-aware features are fed into two-branch reconstruction decoders respectively. In addition, a new feature fusion mechanism, orientation-based feature fusion, is proposed to merge sharp features of the two branches. Both qualitative and quantitative experimental results show that our method performs favorably against the state-of-the-art approaches.