2013
DOI: 10.1109/tvcg.2013.30
|View full text |Cite
|
Sign up to set email alerts
|

Estimating the Gaze of a Virtuality Human

Abstract: The aim of our experiment is to determine if eye-gaze can be estimated from a virtuality human: to within the accuracies that underpin social interaction; and reliably across gaze poses and camera arrangements likely in every day settings. The scene is set by explaining why Immersive Virtuality Telepresence has the potential to meet the grand challenge of faithfully communicating both the appearance and the focus of attention of a remote human participant within a shared 3D computer-supported context. Within t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

4
24
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
4
2

Relationship

2
4

Authors

Journals

citations
Cited by 14 publications
(28 citation statements)
references
References 7 publications
4
24
0
Order By: Relevance
“…Walking participants are head tracked as they try to align to the eye gaze of a static reconstructed model that continuously adjusts for their head position. This is similar to methods employed in "Estimating the gaze of a virtuality human" (Roberts at al, 2013) and Telehuman (Kim et al, 2012).…”
Section: Methodsmentioning
confidence: 86%
See 2 more Smart Citations
“…Walking participants are head tracked as they try to align to the eye gaze of a static reconstructed model that continuously adjusts for their head position. This is similar to methods employed in "Estimating the gaze of a virtuality human" (Roberts at al, 2013) and Telehuman (Kim et al, 2012).…”
Section: Methodsmentioning
confidence: 86%
“…Figure 5 shows box plots comparing the two conditions. All statistics were performed in SPSS comparing within the experiment and against the most similar experiments, Telehuman (Kim et al, 2012) and "Evaluating the gaze of a virtuality human" (Roberts et al, 2013). Differences in the final positions shown in Figures 6a and 6b is potentially explained by the additional difficulty in resolving the eye component of the model.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…However, when what is being responded to is out of view or delayed, the meaning of the response may be lost [1]. At the same time, it is difficult to capture mutual eye gaze, as the camera and display cannot share the same physical position in the space and the user can only look at one of them at a time [6]. On the other hand, VR, in its purer form, immerses people in 3D computer graphics, tracking some of their movements and hence capturing some of the NVC of the user.…”
Section: A Reproducing Nvc In Telepresencementioning
confidence: 99%
“…These approaches attempt to faithfully reproduce appearance, not just movement. Popular 3D reconstruction approaches in this area are shape-from-silhouette [31] and depth-based [32,33]. Both impact on the quality of reproduction in different ways.…”
Section: Approaches To Capturing the Face And Reproducing It In 3dmentioning
confidence: 99%