Real-time depth map estimation for stereoscopic displays with GPU

Wen Chung Kao; Bai Cheng Jeng; Tzu Hung Chen; Zhi Wei Gao

doi:10.1109/ISCE.2011.5973821

Real-time depth map estimation for stereoscopic displays with GPU

Wen Chung Kao^*, Bai Cheng Jeng, Tzu Hung Chen, Zhi Wei Gao

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Given a pair of images, a stereoscopic display should execute the image plane calibration, the depth map estimation, and the multiple views rendering to show a 3-D picture. Among all signal processing stages, the depth estimation is the most critical one. This paper presents a real-time depth map estimation algorithm as well as parallel software architecture based on a GPU processor. The experimental result shows that the proposed algorithm get smooth depth map and the performance can be boosted up to 42X faster than running on a modern traditional personal computer. It achieves the requirement of real-time stereoscopic displays.

Original language	English
Title of host publication	ISCE 2011 - 15th IEEE International Symposium on Consumer Electronics
Pages	228-231
Number of pages	4
DOIs	https://doi.org/10.1109/ISCE.2011.5973821
Publication status	Published - 2011
Event	15th IEEE International Symposium on Consumer Electronics, ISCE 2011 - Singapore, Singapore Duration: 2011 Jun 14 → 2011 Jun 17

Publication series

Name	Proceedings of the International Symposium on Consumer Electronics, ISCE

Other

Other	15th IEEE International Symposium on Consumer Electronics, ISCE 2011
Country/Territory	Singapore
City	Singapore
Period	2011/06/14 → 2011/06/17

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/ISCE.2011.5973821

Cite this

Real-time depth map estimation for stereoscopic displays with GPU. / Kao, Wen Chung; Jeng, Bai Cheng; Chen, Tzu Hung et al.
ISCE 2011 - 15th IEEE International Symposium on Consumer Electronics. 2011. p. 228-231 5973821 (Proceedings of the International Symposium on Consumer Electronics, ISCE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kao, WC, Jeng, BC, Chen, TH & Gao, ZW 2011, Real-time depth map estimation for stereoscopic displays with GPU. in ISCE 2011 - 15th IEEE International Symposium on Consumer Electronics., 5973821, Proceedings of the International Symposium on Consumer Electronics, ISCE, pp. 228-231, 15th IEEE International Symposium on Consumer Electronics, ISCE 2011, Singapore, Singapore, 2011/06/14. https://doi.org/10.1109/ISCE.2011.5973821

@inproceedings{ba2eca3ef71446f0af22f35ceeed4e4f,

title = "Real-time depth map estimation for stereoscopic displays with GPU",

abstract = "Given a pair of images, a stereoscopic display should execute the image plane calibration, the depth map estimation, and the multiple views rendering to show a 3-D picture. Among all signal processing stages, the depth estimation is the most critical one. This paper presents a real-time depth map estimation algorithm as well as parallel software architecture based on a GPU processor. The experimental result shows that the proposed algorithm get smooth depth map and the performance can be boosted up to 42X faster than running on a modern traditional personal computer. It achieves the requirement of real-time stereoscopic displays.",

author = "Kao, {Wen Chung} and Jeng, {Bai Cheng} and Chen, {Tzu Hung} and Gao, {Zhi Wei}",

year = "2011",

doi = "10.1109/ISCE.2011.5973821",

language = "English",

isbn = "9781612848433",

series = "Proceedings of the International Symposium on Consumer Electronics, ISCE",

pages = "228--231",

booktitle = "ISCE 2011 - 15th IEEE International Symposium on Consumer Electronics",

note = "15th IEEE International Symposium on Consumer Electronics, ISCE 2011 ; Conference date: 14-06-2011 Through 17-06-2011",

}

TY - GEN

T1 - Real-time depth map estimation for stereoscopic displays with GPU

AU - Kao, Wen Chung

AU - Jeng, Bai Cheng

AU - Chen, Tzu Hung

AU - Gao, Zhi Wei

PY - 2011

Y1 - 2011

N2 - Given a pair of images, a stereoscopic display should execute the image plane calibration, the depth map estimation, and the multiple views rendering to show a 3-D picture. Among all signal processing stages, the depth estimation is the most critical one. This paper presents a real-time depth map estimation algorithm as well as parallel software architecture based on a GPU processor. The experimental result shows that the proposed algorithm get smooth depth map and the performance can be boosted up to 42X faster than running on a modern traditional personal computer. It achieves the requirement of real-time stereoscopic displays.

AB - Given a pair of images, a stereoscopic display should execute the image plane calibration, the depth map estimation, and the multiple views rendering to show a 3-D picture. Among all signal processing stages, the depth estimation is the most critical one. This paper presents a real-time depth map estimation algorithm as well as parallel software architecture based on a GPU processor. The experimental result shows that the proposed algorithm get smooth depth map and the performance can be boosted up to 42X faster than running on a modern traditional personal computer. It achieves the requirement of real-time stereoscopic displays.

UR - http://www.scopus.com/inward/record.url?scp=80052411597&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052411597&partnerID=8YFLogxK

U2 - 10.1109/ISCE.2011.5973821

DO - 10.1109/ISCE.2011.5973821

M3 - Conference contribution

AN - SCOPUS:80052411597

SN - 9781612848433

T3 - Proceedings of the International Symposium on Consumer Electronics, ISCE

SP - 228

EP - 231

BT - ISCE 2011 - 15th IEEE International Symposium on Consumer Electronics

T2 - 15th IEEE International Symposium on Consumer Electronics, ISCE 2011

Y2 - 14 June 2011 through 17 June 2011

ER -

Real-time depth map estimation for stereoscopic displays with GPU

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this