A Robust Free-Viewpoint Video System for Sport Scenes

Grau, Oliver; Thomas, Graham; Hilton, Adrian; Kilner, J.; Starck, Jonathan

doi:10.1109/3dtv.2007.4379384

Cited by 30 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several methods of reconstructing the human form as a computer model in real time. It is possible to create geometric models of the human form using a technique called shape from silhouette (Grau, et al, 2007) in which multiple viewpoints from cameras allow algorithmic generation of a visual hull (Franco & Boyer, 2003). 3D video has been successfully integrated into ICVE systems that use projectors to surround the user with a virtual environment (Roberts et al, 2015).…”

Section: Literature Reviewmentioning

confidence: 99%

Telethrone Reconstructed; Ongoing Testing Toward a More Natural Situated Display

O'Hare

Fairchild

Wolff

et al. 2017

Augmented Reality and Virtual Reality

View full text Add to dashboard Cite

The concept of supporting ad-hoc or dynamic membership tele-present meetings through pulling up a chair is novel. In real world business situations, people pull up a chair after catching the eye of someone already seated. Telethrone is a situated display on a chair which allows multiple correct views of a remote collaborator. The system has been expanded to support informal meetings where chairs can be moved around. This is facilitated through the novel integration of a 3D reconstructed model of a person, with live viewpoint dependent rendering onto a retro-reflective surface. This removes the need for painstaking alignment of multiple cameras and projectors each time a chair is moved. A between subjects experiment tested accuracy of reconnected mutual gaze mediated by part of the system. Subjectively easier and harder situations are compared. Specifically best and worst cases, both in terms of orientation of eyes in the reconstructed head, and angle of observer gaze onto the display. Discussion compares results to experiments that used other systems to attempt to convey eye gaze by different techniques. This research builds toward a scalable system for adhoc business meetings; a paradigm poorly supported by current video conferencing. It is also applicable to supporting conversations between seated people in any scenario where seats might be moved, for example in interaction between client and therapist in tele-therapy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Telethrone Reconstructed; Ongoing Testing Toward a More Natural Situated Display

O'Hare

Fairchild

Wolff

et al. 2017

Augmented Reality and Virtual Reality

View full text Add to dashboard Cite

show abstract

“…The University of Surrey in cooperation with the BBC developed iview [6]. Their multi-view free viewpoint system is focused on performance and sport events.…”

Section: Related Workmentioning

confidence: 99%

A toolchain for capturing and rendering stereo and multi-view datasets

Klose

Lipski

Ruhl

et al. 2011

2011 International Conference on 3D Imaging (IC3D)

View full text Add to dashboard Cite

We present our toolchain of free-viewpoint video and dynamic scene reconstruction for video and stereoscopic content creation. Our tools take video data from set of sparse unsynchronized cameras and give great freedom during the post production. From input data we can either generate new viewpoints employing the Virtual Video Camera a purely image based system or generate 3D scene models. The approaches are explained and guidelines for weighing their specific advantages and disadvantages in respect to a concrete application are given.

show abstract

“…The recording was made with 15 static cameras arranged around 120 degrees of the stadium [60]. The cameras were interlaced PAL broadcast cameras captured at a resolution of Fig.…”

Section: Capture Environmentmentioning

confidence: 99%

Objective Quality Assessment in Free-Viewpoint Video Production

Starch

Kilner

Hilton

2008

2008 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video

Self Cite

View full text Add to dashboard Cite

This paper addresses the problem of objectively quantifying accuracy in free-viewpoint video production. Freeviewpoint video makes use of geometric scene reconstruction and renders novel views using the appearance sampled in multiple camera images. Previous work typically adopts an objective evaluation of geometric accuracy against ground truth data or a subjective evaluation of visual quality in view synthesis. We consider two production scenarios, human performance capture in a highly constrained studio environment and sports production in a large scale external environment. The accuracy of scene reconstruction is typically limited and absolute geometric accuracy does not necessarily reflect the quality of free-viewpoint rendering. A framework is introduced to quantify error at the point of view synthesis. The approach can be applied as a full-reference metric to measure fidelity to a ground truth image or as a no-reference metric to measure the error in rendering. The framework is applied to a data-set with known geometric accuracy and a comparison is presented for studio-based and sports production scenarios.

show abstract

A Robust Free-Viewpoint Video System for Sport Scenes

Cited by 30 publications

References 12 publications

Telethrone Reconstructed; Ongoing Testing Toward a More Natural Situated Display

Telethrone Reconstructed; Ongoing Testing Toward a More Natural Situated Display

A toolchain for capturing and rendering stereo and multi-view datasets

Objective Quality Assessment in Free-Viewpoint Video Production

Contact Info

Product

Resources

About