Iterative Filter Adaptive Network for Single Image Defocus Deblurring

TL;DR

This paper introduces an end-to-end learning approach with an Iterative Filter Adaptive Network (IFAN) for single image defocus deblurring, effectively handling spatially-varying and large blur through pixel-wise filters and iterative adaptive convolution.

Contribution

The paper presents a novel IFAN architecture that predicts pixel-wise deblurring filters and models large blur with separable filters, improving deblurring performance on real-world images.

Findings

Achieves state-of-the-art results quantitatively.

Outperforms existing methods qualitatively.

Effective handling of spatially-varying and large defocus blur.

Abstract

We propose a novel end-to-end learning-based approach for single image defocus deblurring. The proposed approach is equipped with a novel Iterative Filter Adaptive Network (IFAN) that is specifically designed to handle spatially-varying and large defocus blur. For adaptively handling spatially-varying blur, IFAN predicts pixel-wise deblurring filters, which are applied to defocused features of an input image to generate deblurred features. For effectively managing large blur, IFAN models deblurring filters as stacks of small-sized separable filters. Predicted separable deblurring filters are applied to defocused features using a novel Iterative Adaptive Convolution (IAC) layer. We also propose a training scheme based on defocus disparity estimation and reblurring, which significantly boosts the deblurring quality. We demonstrate that our method achieves state-of-the-art performance both quantitatively and qualitatively on real-world images.