Exploring stereovision-based 3-D scene reconstruction for augmented reality

Guang Yu Nie; Yun Liu; Cong Wang; Yongtian Wang; Yue Liu

doi:10.1109/VR.2019.8797778

Exploring stereovision-based 3-D scene reconstruction for augmented reality

Guang Yu Nie, Yun Liu, Cong Wang, Yongtian Wang, Yue Liu

School of Optics and Photonics

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

3 Citations (Scopus)

Abstract

Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach for 3-D scene reconstruction. In this paper, we explore an improved stereo matching network, SLED-Net, in which a Single Long Encoder-Decoder is proposed to replace the stacked hourglass network in PSM-Net for better contextual information learning. We compare SLED-Net to state-of-the-art methods recently published, and demonstrate its superior performance on Scene Flow and KITTI2015 test sets.

Original language	English
Title of host publication	26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1100-1101
Number of pages	2
ISBN (Electronic)	9781728113777
DOIs	https://doi.org/10.1109/VR.2019.8797778
Publication status	Published - Mar 2019
Event	26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Osaka, Japan Duration: 23 Mar 2019 → 27 Mar 2019

Publication series

Name	26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings

Conference

Conference	26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019
Country/Territory	Japan
City	Osaka
Period	23/03/19 → 27/03/19

Keywords

Computing methodologies
Computing methodologies
Computing methodologies
Mixed/augmented reality
Reconstruction
Scene understanding

Access to Document

10.1109/VR.2019.8797778

Cite this

Nie, G. Y., Liu, Y., Wang, C., Wang, Y., & Liu, Y. (2019). Exploring stereovision-based 3-D scene reconstruction for augmented reality. In 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings (pp. 1100-1101). Article 8797778 (26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VR.2019.8797778

Nie, Guang Yu ; Liu, Yun ; Wang, Cong et al. / Exploring stereovision-based 3-D scene reconstruction for augmented reality. 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1100-1101 (26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings).

@inproceedings{18c7873d21ec4e3eb1e9f820da549b17,

title = "Exploring stereovision-based 3-D scene reconstruction for augmented reality",

abstract = "Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach for 3-D scene reconstruction. In this paper, we explore an improved stereo matching network, SLED-Net, in which a Single Long Encoder-Decoder is proposed to replace the stacked hourglass network in PSM-Net for better contextual information learning. We compare SLED-Net to state-of-the-art methods recently published, and demonstrate its superior performance on Scene Flow and KITTI2015 test sets.",

keywords = "Computing methodologies, Computing methodologies, Computing methodologies, Mixed/augmented reality, Reconstruction, Scene understanding",

author = "Nie, {Guang Yu} and Yun Liu and Cong Wang and Yongtian Wang and Yue Liu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 ; Conference date: 23-03-2019 Through 27-03-2019",

year = "2019",

month = mar,

doi = "10.1109/VR.2019.8797778",

language = "English",

series = "26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1100--1101",

booktitle = "26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings",

address = "United States",

}

Nie, GY, Liu, Y, Wang, C, Wang, Y & Liu, Y 2019, Exploring stereovision-based 3-D scene reconstruction for augmented reality. in 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings., 8797778, 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1100-1101, 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019, Osaka, Japan, 23/03/19. https://doi.org/10.1109/VR.2019.8797778

Exploring stereovision-based 3-D scene reconstruction for augmented reality. / Nie, Guang Yu; Liu, Yun; Wang, Cong et al.
26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1100-1101 8797778 (26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings).

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

TY - GEN

T1 - Exploring stereovision-based 3-D scene reconstruction for augmented reality

AU - Nie, Guang Yu

AU - Liu, Yun

AU - Wang, Cong

AU - Wang, Yongtian

AU - Liu, Yue

PY - 2019/3

Y1 - 2019/3

N2 - Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach for 3-D scene reconstruction. In this paper, we explore an improved stereo matching network, SLED-Net, in which a Single Long Encoder-Decoder is proposed to replace the stacked hourglass network in PSM-Net for better contextual information learning. We compare SLED-Net to state-of-the-art methods recently published, and demonstrate its superior performance on Scene Flow and KITTI2015 test sets.

AB - Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information. Stereo matching is a computer vision based approach for 3-D scene reconstruction. In this paper, we explore an improved stereo matching network, SLED-Net, in which a Single Long Encoder-Decoder is proposed to replace the stacked hourglass network in PSM-Net for better contextual information learning. We compare SLED-Net to state-of-the-art methods recently published, and demonstrate its superior performance on Scene Flow and KITTI2015 test sets.

KW - Computing methodologies

KW - Mixed/augmented reality

KW - Reconstruction

KW - Scene understanding

UR - http://www.scopus.com/inward/record.url?scp=85071876107&partnerID=8YFLogxK

U2 - 10.1109/VR.2019.8797778

DO - 10.1109/VR.2019.8797778

M3 - Conference contribution

AN - SCOPUS:85071876107

T3 - 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings

SP - 1100

EP - 1101

BT - 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019

Y2 - 23 March 2019 through 27 March 2019

ER -

Nie GY, Liu Y, Wang C, Wang Y , Liu Y. Exploring stereovision-based 3-D scene reconstruction for augmented reality. In 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1100-1101. 8797778. (26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings). doi: 10.1109/VR.2019.8797778

Exploring stereovision-based 3-D scene reconstruction for augmented reality

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this