Blur Invariant Kernel-Adaptive Network for Single Image Blind deblurring

TL;DR

This paper introduces a novel blind image deblurring method that estimates blur kernels and restores sharp images using a kernel-adaptive network, achieving state-of-the-art results on multiple datasets.

Contribution

The paper proposes a two-stage approach with a kernel estimation network and a kernel-adaptive deblurring network, advancing blind deblurring techniques.

Findings

Achieves state-of-the-art results on REDS, GOPRO, and Flickr2K datasets.

Effectively estimates image-specific blur kernels.

Improves deblurring performance with kernel-adaptive feature encoding.

Abstract

We present a novel, blind, single image deblurring method that utilizes information regarding blur kernels. Our model solves the deblurring problem by dividing it into two successive tasks: (1) blur kernel estimation and (2) sharp image restoration. We first introduce a kernel estimation network that produces adaptive blur kernels based on the analysis of the blurred image. The network learns the blur pattern of the input image and trains to generate the estimation of image-specific blur kernels. Subsequently, we propose a deblurring network that restores sharp images using the estimated blur kernel. To use the kernel efficiently, we propose a kernel-adaptive AE block that encodes features from both blurred images and blur kernels into a low dimensional space and then decodes them simultaneously to obtain an appropriately synthesized feature representation. We evaluate our model on REDS, GOPRO and Flickr2K datasets using various Gaussian blur kernels. Experiments show that our model can achieve state-of-the-art results on each dataset.