SIDGAN: Efficient Multi-Module Architecture for Single Image Defocus Deblurring

Abstract

In recent years, with the rapid developments in deep learning and graphics processing units, learning-based defocus deblurring has made favorable achievements. However, the current methods are not effective in processing blurred images with a large depth of field. The greater the depth of field, the blurrier the image, namely, the image contains large blurry regions and encounters severe blur. The fundamental reason for the unsatisfactory results is that it is difficult to extract effective features from the blurred images with large blurry regions. For this reason, a new FFEM (Fuzzy Feature Extraction Module) is proposed to enhance the encoder’s ability to extract features from images with large blurry regions. After using the FFEM during encoding, its PSNR (Peak Signal-to-Noise Ratio) is improved by 1.33% on the DPDD (Dual-Pixel Defocus Deblurring). Moreover, images with large blurry regions often cause the current algorithms to generate artifacts in their results. Therefore, a new module named ARM (Artifact Removal Module) is proposed in this work and employed during decoding. After utilizing the ARM during decoding, its PSNR is improved by 2.49% on the DPDD. After using the FFEM and the ARM simultaneously, compared to the latest algorithms, the PSNR of our method is improved by 3.29% on the DPDD. Following the previous research in this field, qualitative and quantitative experiments are conducted on the DPDD and the RealDOF (Real Depth of Field), and the experimental results indicate that our method surpasses the state-of-the-art algorithms in three objective metrics.