Removing Non-Uniform Motion Blur from Images

Sunghyun Cho
POSTECH

Yasuyuki Matsushita
MSR Asia

Seungyong Lee
POSTECH

In Proc. of IEEE International Conference on Computer Vision (ICCV'07), Rio de Janeiro, Brazil, 2007



Abstract

We propose a method for removing non-uniform motion blur from multiple blurry images. Traditional methods focus on estimating a single motion blur kernel for the entire image. In contrast, we aim to restore images blurred by unknown, spatially varying motion blur kernels caused by different relative motions between the camera and the scene. Our algorithm simultaneously estimates multiple motions, motion blur kernels, and the associated image segments. We formulate the problem as a regularized energy function and solve it using an alternating optimization technique. Realworld experiments demonstrate the effectiveness of the proposed method.



Paper
PDF, 7.29MB

Poster
PDF, 6.91MB



BibTex

@ARTICLE{Cho07,
title={Removing Non-Uniform Motion Blur from Images},
author={Sunghyun Cho and Yasuyuki Matsushita and Seungyong Lee},
journal={Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on},
year={2007},
month={Oct.},
volume={},
number={},
pages={1-8},
doi={10.1109/ICCV.2007.4408904},
ISSN={1550-5499}, }