Soft-segmentation guided object motion deblurring

Jinshan Pan, Zhe Hu, Zhixun Su, Hsin Ying Lee, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Citations (Scopus)

Abstract

Object motion blur is a challenging problem as the foreground and the background in the scenes undergo different types of image degradation due to movements in various directions and speed. Most object motion deblurring methods address this problem by segmenting blurred images into regions where different kernels are estimated and applied for restoration. Segmentation on blurred images is difficult due to ambiguous pixels between regions, but it plays an important role for object motion deblurring. To address these problems, we propose a novel model for object motion deblurring. The proposed model is developed based on a maximum a posterior formulation in which soft-segmentation is incorporated for object layer estimation. We propose an efficient algorithm to jointly estimate object segmentation and camera motion where each layer can be deblurred well under the guidance of the soft-segmentation. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art object motion deblurring methods on challenging scenarios.

Original languageEnglish
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages459-468
Number of pages10
ISBN (Electronic)9781467388504
DOIs
Publication statusPublished - 2016 Dec 9
Event29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: 2016 Jun 262016 Jul 1

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2016-December
ISSN (Print)1063-6919

Conference

Conference29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period16/6/2616/7/1

Fingerprint

Restoration
Pixels
Cameras
Degradation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Pan, J., Hu, Z., Su, Z., Lee, H. Y., & Yang, M. H. (2016). Soft-segmentation guided object motion deblurring. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 459-468). [7780425] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.56
Pan, Jinshan ; Hu, Zhe ; Su, Zhixun ; Lee, Hsin Ying ; Yang, Ming Hsuan. / Soft-segmentation guided object motion deblurring. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. pp. 459-468 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{a3d00ef8b414430f8de6665d26a5d235,
title = "Soft-segmentation guided object motion deblurring",
abstract = "Object motion blur is a challenging problem as the foreground and the background in the scenes undergo different types of image degradation due to movements in various directions and speed. Most object motion deblurring methods address this problem by segmenting blurred images into regions where different kernels are estimated and applied for restoration. Segmentation on blurred images is difficult due to ambiguous pixels between regions, but it plays an important role for object motion deblurring. To address these problems, we propose a novel model for object motion deblurring. The proposed model is developed based on a maximum a posterior formulation in which soft-segmentation is incorporated for object layer estimation. We propose an efficient algorithm to jointly estimate object segmentation and camera motion where each layer can be deblurred well under the guidance of the soft-segmentation. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art object motion deblurring methods on challenging scenarios.",
author = "Jinshan Pan and Zhe Hu and Zhixun Su and Lee, {Hsin Ying} and Yang, {Ming Hsuan}",
year = "2016",
month = "12",
day = "9",
doi = "10.1109/CVPR.2016.56",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "459--468",
booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
address = "United States",

}

Pan, J, Hu, Z, Su, Z, Lee, HY & Yang, MH 2016, Soft-segmentation guided object motion deblurring. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780425, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 459-468, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPR.2016.56

Soft-segmentation guided object motion deblurring. / Pan, Jinshan; Hu, Zhe; Su, Zhixun; Lee, Hsin Ying; Yang, Ming Hsuan.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 459-468 7780425 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Soft-segmentation guided object motion deblurring

AU - Pan, Jinshan

AU - Hu, Zhe

AU - Su, Zhixun

AU - Lee, Hsin Ying

AU - Yang, Ming Hsuan

PY - 2016/12/9

Y1 - 2016/12/9

N2 - Object motion blur is a challenging problem as the foreground and the background in the scenes undergo different types of image degradation due to movements in various directions and speed. Most object motion deblurring methods address this problem by segmenting blurred images into regions where different kernels are estimated and applied for restoration. Segmentation on blurred images is difficult due to ambiguous pixels between regions, but it plays an important role for object motion deblurring. To address these problems, we propose a novel model for object motion deblurring. The proposed model is developed based on a maximum a posterior formulation in which soft-segmentation is incorporated for object layer estimation. We propose an efficient algorithm to jointly estimate object segmentation and camera motion where each layer can be deblurred well under the guidance of the soft-segmentation. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art object motion deblurring methods on challenging scenarios.

AB - Object motion blur is a challenging problem as the foreground and the background in the scenes undergo different types of image degradation due to movements in various directions and speed. Most object motion deblurring methods address this problem by segmenting blurred images into regions where different kernels are estimated and applied for restoration. Segmentation on blurred images is difficult due to ambiguous pixels between regions, but it plays an important role for object motion deblurring. To address these problems, we propose a novel model for object motion deblurring. The proposed model is developed based on a maximum a posterior formulation in which soft-segmentation is incorporated for object layer estimation. We propose an efficient algorithm to jointly estimate object segmentation and camera motion where each layer can be deblurred well under the guidance of the soft-segmentation. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art object motion deblurring methods on challenging scenarios.

UR - http://www.scopus.com/inward/record.url?scp=84986300554&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986300554&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.56

DO - 10.1109/CVPR.2016.56

M3 - Conference contribution

AN - SCOPUS:84986300554

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 459

EP - 468

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -

Pan J, Hu Z, Su Z, Lee HY, Yang MH. Soft-segmentation guided object motion deblurring. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 459-468. 7780425. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2016.56