Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 DetailsÜbersicht
  Performance Capture from Sparse Multi-View Video

de Aguiar, E., Theobalt, C., Stoll, C., Ahmed, N., Seidel, H.-P., & Thrun, S. (2008). Performance Capture from Sparse Multi-View Video. In G. Turk (Ed.), Proceedings of ACM SIGGRAPH 2008. New York, NY: ACM.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-1CA4-0 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-BBDB-C
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
de Aguiar, Edilson1, Autor           
Theobalt, Christian1, Autor           
Stoll, Carsten1, Autor           
Ahmed, Naveed1, Autor           
Seidel, Hans-Peter1, Autor           
Thrun, Sebastian, Autor
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: This paper proposes a new marker-less approach to capturing human performances from multi-view video. Our algorithm can jointly reconstruct spatio-temporally coherent geometry, motion and textural surface appearance of actors that perform complex and rapid moves. Furthermore, since our algorithm is purely meshbased and makes as few as possible prior assumptions about the type of subject being tracked, it can even capture performances of people wearing wide apparel, such as a dancer wearing a skirt. To serve this purpose our method efficiently and effectively combines the power of surface- and volume-based shape deformation techniques with a new mesh-based analysis-through-synthesis framework. This framework extracts motion constraints from video and makes the laser-scan of the tracked subject mimic the recorded performance. Also small-scale time-varying shape detail is recovered by applying model-guided multi-view stereo to refine the model surface. Our method delivers captured performance data at higher level of detail, is highly versatile, and is applicable to many complex types of scenes that could not be handled by alternative marker-based or marker-free recording techniques.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2009-03-252008
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: eDoc: 428027
DOI: 10.1145/1360612.1360697
URI: http://doi.acm.org/10.1145/1360612.1360697
Anderer: Local-ID: C125756E0038A185-2E696CF3894EE2D9C125755400496998-deAguiar2008
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Untitled Event
Veranstaltungsort: Los Angeles, USA
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Proceedings of ACM SIGGRAPH 2008
Genre der Quelle: Konferenzband
 Urheber:
Turk, Greg, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: New York, NY : ACM
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: - Identifikator: -

Quelle 2

einblenden:
ausblenden:
Titel: ACM Transactions on Graphics
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: - Identifikator: -