Gaussian Kernel Mixture Network for Single Image Defocus Deblurring

Yuhui Quan, Zicong Wu, Hui Ji

Keywords: Defocus Deblurring, Deep Learning, Image Recovery, Unrolling, Attention

TL;DR: A lightweight DNN for single image defocus deblurring with SOTA performance

Abstract: Defocus blur is one kind of blur effects often seen in images, which is challenging to remove due to its spatially variant amount. This paper presents an end-to-end deep learning approach for removing defocus blur from a single image, so as to have an all-in-focus image for consequent vision tasks. First, a pixel-wise Gaussian kernel mixture (GKM) model is proposed for representing spatially variant defocus blur kernels in an efficient linear parametric form, with higher accuracy than existing models. Then, a deep neural network called GKMNet is developed by unrolling a fixed-point iteration of the GKM-based deblurring. The GKMNet is built on a lightweight scale-recurrent architecture, with a scale-recurrent attention module for estimating the mixing coefficients in GKM for defocus deblurring. Extensive experiments show that the GKMNet not only noticeably outperforms existing defocus deblurring methods, but also has its advantages in terms of model complexity and computational efficiency.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/csZcWu/GKMNet

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2111.00454/code)