Coherent Spatiotemporal Filtering, Upsampling and Rendering of RGBZ Videos

Sophisticated video processing effects require both image and geometry information. We explore the possibility to augment a video camera with a recent infrared time‐of‐flight depth camera, to capture high‐resolution RGB and low‐resolution, noisy depth at video frame rates. To turn such a setup into...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer graphics forum 2012-05, Vol.31 (2pt1), p.247-256
Hauptverfasser: Richardt, Christian, Stoll, Carsten, Dodgson, Neil A., Seidel, Hans-Peter, Theobalt, Christian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Sophisticated video processing effects require both image and geometry information. We explore the possibility to augment a video camera with a recent infrared time‐of‐flight depth camera, to capture high‐resolution RGB and low‐resolution, noisy depth at video frame rates. To turn such a setup into a practical RGBZ video camera, we develop efficient data filtering techniques that are tailored to the noise characteristics of IR depth cameras. We first remove typical artefacts in the RGBZ data and then apply an efficient spatiotemporal denoising and upsampling scheme. This allows us to record temporally coherent RGBZ videos at interactive frame rates and to use them to render a variety of effects in unprecedented quality. We show effects such as video relighting, geometry‐based ion and stylisation, background segmentation and rendering in stereoscopic 3D.
ISSN:0167-7055
1467-8659
DOI:10.1111/j.1467-8659.2012.03003.x