Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks

TL;DR

This paper introduces a novel deep learning approach for motion deblurring that explicitly estimates pixel-wise motion kernels, leading to more accurate and explainable deblurring results compared to traditional end-to-end methods.

Contribution

It proposes a two-network framework that estimates dense non-uniform motion blur kernels and performs non-blind deconvolution, enhancing generalization and interpretability.

Findings

Kernel prediction network accurately estimates motion blur kernels.

The deblurring pipeline outperforms existing end-to-end deep learning methods.

Results are competitive or superior on real blurred images.

Abstract

In recent years, the removal of motion blur in photographs has seen impressive progress in the hands of deep learning-based methods, trained to map directly from blurry to sharp images. For this reason, approaches that explicitly use a forward degradation model received significantly less attention. However, a well-defined specification of the blur genesis, as an intermediate step, promotes the generalization and explainability of the method. Towards this goal, we propose a learning-based motion deblurring method based on dense non-uniform motion blur estimation followed by a non-blind deconvolution approach. Specifically, given a blurry image, a first network estimates the dense per-pixel motion blur kernels using a lightweight representation composed of a set of image-adaptive basis motion kernels and the corresponding mixing coefficients. Then, a second network trained jointly with the first one, unrolls a non-blind deconvolution method using the motion kernel field estimated by the first network. The model-driven aspect is further promoted by training the networks on sharp/blurry pairs synthesized according to a convolution-based, non-uniform motion blur degradation model. Qualitative and quantitative evaluation shows that the kernel prediction network produces accurate motion blur estimates, and that the deblurring pipeline leads to restorations of real blurred images that are competitive or superior to those obtained with existing end-to-end deep learning-based methods. Code and trained models are available at https://github.com/GuillermoCarbajal/J-MKPD/.