Learning to Deblur

TL;DR

This paper presents a deep learning-based method for blind image deconvolution that combines neural network components with domain-specific computations, trained end-to-end for improved performance.

Contribution

It introduces a novel layered architecture that integrates neural network learning with image deconvolution techniques, trained on artificial data for enhanced blind deblurring.

Findings

Achieves competitive quality in blind deconvolution

Offers faster runtime compared to traditional methods

Demonstrates effective end-to-end training on synthetic data

Abstract

We describe a learning-based approach to blind image deconvolution. It uses a deep layered architecture, parts of which are borrowed from recent work on neural network learning, and parts of which incorporate computations that are specific to image deconvolution. The system is trained end-to-end on a set of artificially generated training examples, enabling competitive performance in blind deconvolution, both with respect to quality and runtime.