# Motion Blur removal via Coupled Autoencoder

## TL;DR

This paper introduces a coupled autoencoder approach for motion blur removal, framing deblurring as a transfer learning problem, which enables faster, on-the-fly image restoration with improved quality over existing methods.

## Contribution

It presents a novel formulation that recasts deblurring as transfer learning and employs a coupled autoencoder for simultaneous learning of weights and coupling maps.

## Key findings

- Outperforms state-of-the-art techniques in image quality
- Operates faster without costly inverse problems
- Effective for real-time motion blur removal

## Abstract

In this paper a joint optimization technique has been proposed for coupled autoencoder which learns the autoencoder weights and coupling map (between source and target) simultaneously. The technique is applicable to any transfer learning problem. In this work, we propose a new formulation that recasts deblurring as a transfer learning problem, it is solved using the proposed coupled autoencoder. The proposed technique can operate on-the-fly, since it does not require solving any costly inverse problem. Experiments have been carried out on state-of-the-art techniques, our method yields better quality images in shorter operating times.