Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

TL;DR

This paper introduces MLWNet, a multi-scale deep learning network utilizing a learnable discrete wavelet transform to improve blind motion deblurring, achieving state-of-the-art results with simplified architecture and enhanced detail preservation.

Contribution

The paper proposes a novel multi-scale network with a learnable wavelet transform module, reducing complexity and improving detail recovery in motion deblurring tasks.

Findings

Achieves state-of-the-art performance on real-world datasets.

Improves detail preservation and frequency feature focus.

Reduces algorithmic complexity compared to traditional coarse-to-fine methods.

Abstract

Coarse-to-fine schemes are widely used in traditional single-image motion deblur; however, in the context of deep learning, existing multi-scale algorithms not only require the use of complex modules for feature fusion of low-scale RGB images and deep semantics, but also manually generate low-resolution pairs of images that do not have sufficient confidence. In this work, we propose a multi-scale network based on single-input and multiple-outputs(SIMO) for motion deblurring. This simplifies the complexity of algorithms based on a coarse-to-fine scheme. To alleviate restoration defects impacting detail information brought about by using a multi-scale architecture, we combine the characteristics of real-world blurring trajectories with a learnable wavelet transform module to focus on the directional continuity and frequency features of the step-by-step transitions between blurred images to sharp images. In conclusion, we propose a multi-scale network with a learnable discrete wavelet transform (MLWNet), which exhibits state-of-the-art performance on multiple real-world deblurred datasets, in terms of both subjective and objective quality as well as computational efficiency.