Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency

TL;DR

This paper introduces a novel end-to-end deep learning architecture using Atrous Spatial Pyramid Deformable Convolution modules and a reblurring consistency constraint to effectively address non-uniform motion blur, outperforming existing methods.

Contribution

The paper proposes a new ASPDC-based network with pixel-specific motion learning and a reblurring strategy for improved non-uniform motion deblurring.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Implicitly learns pixel-specific motion with multiple dilation rates

Uses reblurring constraint to enhance training stability

Abstract

Many deep learning based methods are designed to remove non-uniform (spatially variant) motion blur caused by object motion and camera shake without knowing the blur kernel. Some methods directly output the latent sharp image in one stage, while others utilize a multi-stage strategy (\eg multi-scale, multi-patch, or multi-temporal) to gradually restore the sharp image. However, these methods have the following two main issues: 1) The computational cost of multi-stage is high; 2) The same convolution kernel is applied in different regions, which is not an ideal choice for non-uniform blur. Hence, non-uniform motion deblurring is still a challenging and open problem. In this paper, we propose a new architecture which consists of multiple Atrous Spatial Pyramid Deformable Convolution (ASPDC) modules to deblur an image end-to-end with more flexibility. Multiple ASPDC modules implicitly learn the pixel-specific motion with different dilation rates in the same layer to handle movements of different magnitude. To improve the training, we also propose a reblurring network to map the deblurred output back to the blurred input, which constrains the solution space. Our experimental results show that the proposed method outperforms state-of-the-art methods on the benchmark datasets. The code is available at https://github.com/Dong-Huo/ASPDC.