Fast non-uniform deblurring using constrained camera pose subspace

Research output: Contribution to conferencePaper

39 Citations (Scopus)

Abstract

Camera shake during exposure time often results in non-uniform blur across the entire image. Recent algorithms model the non-uniform blurry image as a linear combination of images observed by the camera at discretized poses, and focus on estimating the time fraction positioned at each pose. While these algorithms show promising results, they nevertheless entail heavy computational loads. In this work, we propose a novel single image deblurring algorithm to remove non-uniform blur. We estimate the local blur kernels at different image regions and obtain an initial guess of possible camera poses using backprojection. By restraining the possible camera poses in a low-dimensional subspace, we iteratively estimate the weight for each pose in the camera pose space. Experimental validations with the state-of-the-art methods demonstrate the efficiency and effectiveness of our algorithm for non-uniform deblurring.

Original languageEnglish
DOIs
Publication statusPublished - 2012 Jan 1
Event2012 23rd British Machine Vision Conference, BMVC 2012 - Guildford, Surrey, United Kingdom
Duration: 2012 Sep 32012 Sep 7

Other

Other2012 23rd British Machine Vision Conference, BMVC 2012
CountryUnited Kingdom
CityGuildford, Surrey
Period12/9/312/9/7

Fingerprint

Cameras

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Hu, Z., & Yang, M. H. (2012). Fast non-uniform deblurring using constrained camera pose subspace. Paper presented at 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom. https://doi.org/10.5244/C.26.136
Hu, Zhe ; Yang, Ming Hsuan. / Fast non-uniform deblurring using constrained camera pose subspace. Paper presented at 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom.
@conference{dbb683c1f9cd4a938c3930a03934e839,
title = "Fast non-uniform deblurring using constrained camera pose subspace",
abstract = "Camera shake during exposure time often results in non-uniform blur across the entire image. Recent algorithms model the non-uniform blurry image as a linear combination of images observed by the camera at discretized poses, and focus on estimating the time fraction positioned at each pose. While these algorithms show promising results, they nevertheless entail heavy computational loads. In this work, we propose a novel single image deblurring algorithm to remove non-uniform blur. We estimate the local blur kernels at different image regions and obtain an initial guess of possible camera poses using backprojection. By restraining the possible camera poses in a low-dimensional subspace, we iteratively estimate the weight for each pose in the camera pose space. Experimental validations with the state-of-the-art methods demonstrate the efficiency and effectiveness of our algorithm for non-uniform deblurring.",
author = "Zhe Hu and Yang, {Ming Hsuan}",
year = "2012",
month = "1",
day = "1",
doi = "10.5244/C.26.136",
language = "English",
note = "2012 23rd British Machine Vision Conference, BMVC 2012 ; Conference date: 03-09-2012 Through 07-09-2012",

}

Hu, Z & Yang, MH 2012, 'Fast non-uniform deblurring using constrained camera pose subspace', Paper presented at 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom, 12/9/3 - 12/9/7. https://doi.org/10.5244/C.26.136

Fast non-uniform deblurring using constrained camera pose subspace. / Hu, Zhe; Yang, Ming Hsuan.

2012. Paper presented at 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Fast non-uniform deblurring using constrained camera pose subspace

AU - Hu, Zhe

AU - Yang, Ming Hsuan

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Camera shake during exposure time often results in non-uniform blur across the entire image. Recent algorithms model the non-uniform blurry image as a linear combination of images observed by the camera at discretized poses, and focus on estimating the time fraction positioned at each pose. While these algorithms show promising results, they nevertheless entail heavy computational loads. In this work, we propose a novel single image deblurring algorithm to remove non-uniform blur. We estimate the local blur kernels at different image regions and obtain an initial guess of possible camera poses using backprojection. By restraining the possible camera poses in a low-dimensional subspace, we iteratively estimate the weight for each pose in the camera pose space. Experimental validations with the state-of-the-art methods demonstrate the efficiency and effectiveness of our algorithm for non-uniform deblurring.

AB - Camera shake during exposure time often results in non-uniform blur across the entire image. Recent algorithms model the non-uniform blurry image as a linear combination of images observed by the camera at discretized poses, and focus on estimating the time fraction positioned at each pose. While these algorithms show promising results, they nevertheless entail heavy computational loads. In this work, we propose a novel single image deblurring algorithm to remove non-uniform blur. We estimate the local blur kernels at different image regions and obtain an initial guess of possible camera poses using backprojection. By restraining the possible camera poses in a low-dimensional subspace, we iteratively estimate the weight for each pose in the camera pose space. Experimental validations with the state-of-the-art methods demonstrate the efficiency and effectiveness of our algorithm for non-uniform deblurring.

UR - http://www.scopus.com/inward/record.url?scp=84898450347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898450347&partnerID=8YFLogxK

U2 - 10.5244/C.26.136

DO - 10.5244/C.26.136

M3 - Paper

AN - SCOPUS:84898450347

ER -

Hu Z, Yang MH. Fast non-uniform deblurring using constrained camera pose subspace. 2012. Paper presented at 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom. https://doi.org/10.5244/C.26.136