MRNET: Multi-Refinement Network for Dual-Pixel Images Defocus Deblurring

Defocus blurring is an inevitable phenomenon in cameras. Though many methods have been proposed, the problem is still challenging because of their low deblurring performance and long processing time. To solve this problem, we propose an efficient Multi-Refinement Network (MRNet) for dual-pixel images defocus deblurring. The MRNet contains two core modules that are alignment module and reconstruction module, respectively. We design a Siamese Pyramid Network (SPN) as alignment module to alleviate the misalignment problem of left and right views. At the same time, a Multi-Scale Residuals Group Module (MSRGM) is proposed in the reconstruction module, which can extract and fuse features from different scales to obtain better deblurring performance. Specifically, the reconstruction module is composed of multiple MSRGM modules, and each MSRGM is a refinement of the previous one, which is our leitmotif - Multi-Refinement. Experimental results on the popular benchmarks show that the proposed method can significantly improve the performance of defocus deblurring.

1. INTRODUCTION

Defocus blurring is a common phenomenon in the cameras, especially when taking photos with the mobile phone. It always brings many disadvantages, such as image quality degradation and bad performance of computer vision tasks. In order to restore the blurred image to clarity, researchers have done a lot of excellent works [1], [2], [3], [4], [5]. Researchers proposed the two-stage approaches in the initial phase of study. First, generating defocus blurring map. Then, removing defocus blurring according to the blurring map. However, the two-stage methods heavily rely on the accuracy of defocus blurring map, which limits the performance of deblurring.