Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis

Chih Fan Chen; Evan Suma Rosenberg

doi:10.1109/VR.2018.8446410

Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis

Chih Fan Chen, Evan Suma Rosenberg

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

2 Scopus citations

Abstract

We present a dynamic omnidirectional texture synthesis (DOTS) approach for generating real-Time virtual reality content captured using a consumer-grade RGB-D camera. Compared to a single fixed-viewpoint color map, view-dependent texture mapping (VDTM) techniques can reproduce finer detail and replicate dynamic lighting effects that become especially noticeable with head tracking in virtual reality. However, VDTM is very sensitive to errors such as missing data or inaccurate camera pose estimation, both of which are commonplace for objects captured using consumer-grade RGB-D cameras. To overcome these limitations, our proposed optimization can synthesize a high resolution view-dependent texture map for any virtual camera location. Synthetic textures are generated by uniformly sampling a spherical virtual camera set surrounding the virtual object, thereby enabling efficient real-Time rendering for all potential viewing directions.

Original language	English (US)
Title of host publication	25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings
Editors	Frank Steinicke, Bruce Thomas, Kiyoshi Kiyokawa, Greg Welch
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	521-522
Number of pages	2
ISBN (Print)	9781538633656
DOIs	https://doi.org/10.1109/VR.2018.8446410
State	Published - Aug 24 2018
Externally published	Yes
Event	25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Reutlingen, Germany Duration: Mar 18 2018 → Mar 22 2018

Publication series

Name	25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings

Other

Other	25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018
Country/Territory	Germany
City	Reutlingen
Period	3/18/18 → 3/22/18

Bibliographical note

Funding Information:
This work is sponsored by the U.S. Army Research Laboratory (ARL) under contract number W911NF-14-D-0005. Statements

Keywords

content creation
view-dependent texture mapping
virtual reality

Access

10.1109/VR.2018.8446410

OpenUrl availability

Full text

Cite this

Chen, C. F., & Rosenberg, E. S. (2018). Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis. In F. Steinicke, B. Thomas, K. Kiyokawa, & G. Welch (Eds.), 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings (pp. 521-522). Article 8446410 (25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VR.2018.8446410

Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis. / Chen, Chih Fan; Rosenberg, Evan Suma.
25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings. ed. / Frank Steinicke; Bruce Thomas; Kiyoshi Kiyokawa; Greg Welch. Institute of Electrical and Electronics Engineers Inc., 2018. p. 521-522 8446410 (25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings).

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

Chen, CF & Rosenberg, ES 2018, Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis. in F Steinicke, B Thomas, K Kiyokawa & G Welch (eds), 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings., 8446410, 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 521-522, 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018, Reutlingen, Germany, 3/18/18. https://doi.org/10.1109/VR.2018.8446410

Chen CF, Rosenberg ES. Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis. In Steinicke F, Thomas B, Kiyokawa K, Welch G, editors, 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 521-522. 8446410. (25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings). doi: 10.1109/VR.2018.8446410

Chen, Chih Fan ; Rosenberg, Evan Suma. / Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis. 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings. editor / Frank Steinicke ; Bruce Thomas ; Kiyoshi Kiyokawa ; Greg Welch. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 521-522 (25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings).

@inproceedings{bb9d4f8775f54dccbd4e6a7c353b0afe,

title = "Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis",

abstract = "We present a dynamic omnidirectional texture synthesis (DOTS) approach for generating real-Time virtual reality content captured using a consumer-grade RGB-D camera. Compared to a single fixed-viewpoint color map, view-dependent texture mapping (VDTM) techniques can reproduce finer detail and replicate dynamic lighting effects that become especially noticeable with head tracking in virtual reality. However, VDTM is very sensitive to errors such as missing data or inaccurate camera pose estimation, both of which are commonplace for objects captured using consumer-grade RGB-D cameras. To overcome these limitations, our proposed optimization can synthesize a high resolution view-dependent texture map for any virtual camera location. Synthetic textures are generated by uniformly sampling a spherical virtual camera set surrounding the virtual object, thereby enabling efficient real-Time rendering for all potential viewing directions.",

keywords = "content creation, view-dependent texture mapping, virtual reality",

author = "Chen, {Chih Fan} and Rosenberg, {Evan Suma}",

note = "Funding Information: This work is sponsored by the U.S. Army Research Laboratory (ARL) under contract number W911NF-14-D-0005. Statements; 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 ; Conference date: 18-03-2018 Through 22-03-2018",

year = "2018",

month = aug,

day = "24",

doi = "10.1109/VR.2018.8446410",

language = "English (US)",

isbn = "9781538633656",

series = "25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings",

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

pages = "521--522",

editor = "Frank Steinicke and Bruce Thomas and Kiyoshi Kiyokawa and Greg Welch",

booktitle = "25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings",

}

TY - GEN

T1 - Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis

AU - Chen, Chih Fan

AU - Rosenberg, Evan Suma

N1 - Funding Information: This work is sponsored by the U.S. Army Research Laboratory (ARL) under contract number W911NF-14-D-0005. Statements

PY - 2018/8/24

Y1 - 2018/8/24

N2 - We present a dynamic omnidirectional texture synthesis (DOTS) approach for generating real-Time virtual reality content captured using a consumer-grade RGB-D camera. Compared to a single fixed-viewpoint color map, view-dependent texture mapping (VDTM) techniques can reproduce finer detail and replicate dynamic lighting effects that become especially noticeable with head tracking in virtual reality. However, VDTM is very sensitive to errors such as missing data or inaccurate camera pose estimation, both of which are commonplace for objects captured using consumer-grade RGB-D cameras. To overcome these limitations, our proposed optimization can synthesize a high resolution view-dependent texture map for any virtual camera location. Synthetic textures are generated by uniformly sampling a spherical virtual camera set surrounding the virtual object, thereby enabling efficient real-Time rendering for all potential viewing directions.

AB - We present a dynamic omnidirectional texture synthesis (DOTS) approach for generating real-Time virtual reality content captured using a consumer-grade RGB-D camera. Compared to a single fixed-viewpoint color map, view-dependent texture mapping (VDTM) techniques can reproduce finer detail and replicate dynamic lighting effects that become especially noticeable with head tracking in virtual reality. However, VDTM is very sensitive to errors such as missing data or inaccurate camera pose estimation, both of which are commonplace for objects captured using consumer-grade RGB-D cameras. To overcome these limitations, our proposed optimization can synthesize a high resolution view-dependent texture map for any virtual camera location. Synthetic textures are generated by uniformly sampling a spherical virtual camera set surrounding the virtual object, thereby enabling efficient real-Time rendering for all potential viewing directions.

KW - content creation

KW - view-dependent texture mapping

KW - virtual reality

UR - http://www.scopus.com/inward/record.url?scp=85053824068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053824068&partnerID=8YFLogxK

U2 - 10.1109/VR.2018.8446410

DO - 10.1109/VR.2018.8446410

M3 - Conference contribution

AN - SCOPUS:85053824068

SN - 9781538633656

T3 - 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings

SP - 521

EP - 522

BT - 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018 - Proceedings

A2 - Steinicke, Frank

A2 - Thomas, Bruce

A2 - Kiyokawa, Kiyoshi

A2 - Welch, Greg

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 25th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2018

Y2 - 18 March 2018 through 22 March 2018

ER -

Virtual Content Creation Using Dynamic Omnidirectional Texture Synthesis

Abstract

Publication series

Other

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this