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

光电学院

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

4 引用（Scopus）

摘要

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.

源语言	英语
主期刊名	26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings
出版商	Institute of Electrical and Electronics Engineers Inc.
页	1100-1101
页数	2
ISBN（电子版）	9781728113777
DOI	https://doi.org/10.1109/VR.2019.8797778
出版状态	已出版 - 3月 2019
活动	26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Osaka, 日本期限: 23 3月 2019 → 27 3月 2019

出版系列

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

会议

会议	26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019
国家/地区	日本
市	Osaka
时期	23/03/19 → 27/03/19

访问文件

10.1109/VR.2019.8797778

其它文件与链接

链接到 Scopus 的出版物

引用此

Nie, G. Y., Liu, Y., Wang, C., Wang, Y., & Liu, Y. (2019). Exploring stereovision-based 3-D scene reconstruction for augmented reality. 在 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings (页码 1100-1101). 文章 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 等. / 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. 页码 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. 在 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., 页码 1100-1101, 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019, Osaka, 日本, 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 等.
26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 页码 1100-1101 8797778 (26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

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 - https://www.scopus.com/pages/publications/85071876107

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. 在 26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 页码 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

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此