Depth image-based rendering with low resolution depth

Quang H. Nguyen, Minh N. Do, Sanjay J. Patel

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

Abstract

This paper proposes a new approach for depth image-based rendering (DIBR) with low resolution depth using the 3D propagation algorithm. Our novel depth edge enhancement method efficiently corrects and sharpens the depth edges in the propagated depth image using available high resolution color information. Experimental results show that only with 4% depth information kept for low resolution depth image, the proposed method can provide comparable rendering quality to that of the high resolution case. Furthermore, the proposed work is developed to match the fine-grain parallelism of general-purpose graphics processing units (GPGPUs) and hence can be accelerated to nearly real-time operations in low cost DIBR systems.

Original languageEnglish (US)
Title of host publication2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
PublisherIEEE Computer Society
Pages553-556
Number of pages4
ISBN (Print)9781424456543
DOIs
StatePublished - Jan 1 2009
Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
Duration: Nov 7 2009Nov 10 2009

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Other

Other2009 IEEE International Conference on Image Processing, ICIP 2009
CountryEgypt
CityCairo
Period11/7/0911/10/09

Fingerprint

Color
Costs
Graphics processing unit

Keywords

  • Depth image enhancement
  • Depth image-based rendering
  • Parallelism

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Nguyen, Q. H., Do, M. N., & Patel, S. J. (2009). Depth image-based rendering with low resolution depth. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings (pp. 553-556). [5413896] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2009.5413896

Depth image-based rendering with low resolution depth. / Nguyen, Quang H.; Do, Minh N.; Patel, Sanjay J.

2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. p. 553-556 5413896 (Proceedings - International Conference on Image Processing, ICIP).

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

Nguyen, QH, Do, MN & Patel, SJ 2009, Depth image-based rendering with low resolution depth. in 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings., 5413896, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 553-556, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 11/7/09. https://doi.org/10.1109/ICIP.2009.5413896
Nguyen QH, Do MN, Patel SJ. Depth image-based rendering with low resolution depth. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society. 2009. p. 553-556. 5413896. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2009.5413896
Nguyen, Quang H. ; Do, Minh N. ; Patel, Sanjay J. / Depth image-based rendering with low resolution depth. 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. pp. 553-556 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{e7088c117b2d4e8d8f398fb943f9f348,
title = "Depth image-based rendering with low resolution depth",
abstract = "This paper proposes a new approach for depth image-based rendering (DIBR) with low resolution depth using the 3D propagation algorithm. Our novel depth edge enhancement method efficiently corrects and sharpens the depth edges in the propagated depth image using available high resolution color information. Experimental results show that only with 4{\%} depth information kept for low resolution depth image, the proposed method can provide comparable rendering quality to that of the high resolution case. Furthermore, the proposed work is developed to match the fine-grain parallelism of general-purpose graphics processing units (GPGPUs) and hence can be accelerated to nearly real-time operations in low cost DIBR systems.",
keywords = "Depth image enhancement, Depth image-based rendering, Parallelism",
author = "Nguyen, {Quang H.} and Do, {Minh N.} and Patel, {Sanjay J.}",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/ICIP.2009.5413896",
language = "English (US)",
isbn = "9781424456543",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "553--556",
booktitle = "2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings",

}

TY - GEN

T1 - Depth image-based rendering with low resolution depth

AU - Nguyen, Quang H.

AU - Do, Minh N.

AU - Patel, Sanjay J.

PY - 2009/1/1

Y1 - 2009/1/1

N2 - This paper proposes a new approach for depth image-based rendering (DIBR) with low resolution depth using the 3D propagation algorithm. Our novel depth edge enhancement method efficiently corrects and sharpens the depth edges in the propagated depth image using available high resolution color information. Experimental results show that only with 4% depth information kept for low resolution depth image, the proposed method can provide comparable rendering quality to that of the high resolution case. Furthermore, the proposed work is developed to match the fine-grain parallelism of general-purpose graphics processing units (GPGPUs) and hence can be accelerated to nearly real-time operations in low cost DIBR systems.

AB - This paper proposes a new approach for depth image-based rendering (DIBR) with low resolution depth using the 3D propagation algorithm. Our novel depth edge enhancement method efficiently corrects and sharpens the depth edges in the propagated depth image using available high resolution color information. Experimental results show that only with 4% depth information kept for low resolution depth image, the proposed method can provide comparable rendering quality to that of the high resolution case. Furthermore, the proposed work is developed to match the fine-grain parallelism of general-purpose graphics processing units (GPGPUs) and hence can be accelerated to nearly real-time operations in low cost DIBR systems.

KW - Depth image enhancement

KW - Depth image-based rendering

KW - Parallelism

UR - http://www.scopus.com/inward/record.url?scp=77951941148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951941148&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5413896

DO - 10.1109/ICIP.2009.5413896

M3 - Conference contribution

AN - SCOPUS:77951941148

SN - 9781424456543

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 553

EP - 556

BT - 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings

PB - IEEE Computer Society

ER -