Welcome to the IKCEST

22ND ACM CONFERENCE ON VIRTUAL REALITY SOFTWARE AND TECHNOLOGY (VRST 2016) | Vol., Issue. | | Pages 10

22ND ACM CONFERENCE ON VIRTUAL REALITY SOFTWARE AND TECHNOLOGY (VRST 2016)

Multi-View Gesture Annotations in Image-based 3D Reconstructed Scenes

Turk, M    Lien, KC    Nuernberger, B    Sweeney, C    Hollerer, T   Grinta, L   
Abstract

We present a novel 2D gesture annotation method for use in image-based 3D reconstructed scenes with applications in collaborative virtual and augmented reality. Image-based reconstructions allow users to virtually explore a remote environment using image-based rendering techniques. To collaborate with other users, either synchronously or asynchronously, simple 2D gesture annotations can be used to convey spatial information to another user. Unfortunately, prior methods are either unable to disambiguate such 2D annotations in 3D from novel viewpoints or require relatively dense reconstructions of the environment. ;In this paper, we propose a simple multi-view annotation method that is useful in a variety of scenarios and applicable to both very sparse and dense 3D reconstructions. Specifically, we employ interactive disambiguation of the 2D gestures via a second annotation drawn from another viewpoint, triangulating two drawings to achieve a 3D result. Our method automatically chooses an appropriate second viewpoint and uses image-based rendering transitions to keep the user oriented while moving to the second viewpoint. User experiments in an asynchronous collaboration scenario demonstrate the usability of the method and its superiority over a baseline method. In addition, we showcase our method running on a variety of image-based reconstruction datasets and highlight its use in a synchronous local-remote user collaboration system.

Original Text (This is the original text for your reference.)

Multi-View Gesture Annotations in Image-based 3D Reconstructed Scenes

We present a novel 2D gesture annotation method for use in image-based 3D reconstructed scenes with applications in collaborative virtual and augmented reality. Image-based reconstructions allow users to virtually explore a remote environment using image-based rendering techniques. To collaborate with other users, either synchronously or asynchronously, simple 2D gesture annotations can be used to convey spatial information to another user. Unfortunately, prior methods are either unable to disambiguate such 2D annotations in 3D from novel viewpoints or require relatively dense reconstructions of the environment. ;In this paper, we propose a simple multi-view annotation method that is useful in a variety of scenarios and applicable to both very sparse and dense 3D reconstructions. Specifically, we employ interactive disambiguation of the 2D gestures via a second annotation drawn from another viewpoint, triangulating two drawings to achieve a 3D result. Our method automatically chooses an appropriate second viewpoint and uses image-based rendering transitions to keep the user oriented while moving to the second viewpoint. User experiments in an asynchronous collaboration scenario demonstrate the usability of the method and its superiority over a baseline method. In addition, we showcase our method running on a variety of image-based reconstruction datasets and highlight its use in a synchronous local-remote user collaboration system.

+More

Cite this article
APA

APA

MLA

Chicago

Turk, M ,Lien, KC ,Nuernberger, B ,Sweeney, C ,Hollerer, T,Grinta, L ,.Multi-View Gesture Annotations in Image-based 3D Reconstructed Scenes. (),10.

Disclaimer: The translated content is provided by third-party translation service providers, and IKCEST shall not assume any responsibility for the accuracy and legality of the content.
Translate engine
Article's language
English
中文
Pусск
Français
Español
العربية
Português
Kikongo
Dutch
kiswahili
هَوُسَ
IsiZulu
Action
Recommended articles

Report

Select your report category*



Reason*



By pressing send, your feedback will be used to improve IKCEST. Your privacy will be protected.

Submit
Cancel