Details
| Original language | English |
|---|---|
| Title of host publication | 2007 3DTV Conference |
| Editors | Georgios Triantafyllidis |
| Publication status | Published - 2007 |
| Event | 1st International Conference on 3DTV, 3DTV-CON 2007 - Kos, Greece Duration: 7 May 2007 → 9 May 2007 |
Publication series
| Name | Proceedings of 3DTV-CON |
|---|---|
| ISSN (Print) | 2161-2021 |
| ISSN (electronic) | 2161-203X |
Abstract
In this paper we propose a novel method to create dynamic mesh sequences with fixed connectivity from multiple camera video streams. Fixed connectivity is useful for dynamic mesh coding as mesh connectivity has to be transmitted only once and not frame-wise. The proposed method runs automatically. It deploys mesh parametrizations and voronoi diagrams from the computer graphics realm as well as 2D optical and 3D scene flow from computer vision. Assuming that a given dynamic mesh sequence does not necessarily have constant connectivity, motion estimation is performed by applying a 3D motion field to a static reconstruction in one frame. Afterwards, mesh connectivity is transferred patch-wise from one frame to the next one using remeshing techniques. The entire method is independent of static mesh resolution, hence supplying a basis for dynamic mesh coding and simplification.
Keywords
- 3D mesh representation, 3D motion analysis and tracking, 3D motion animation, Multi-view image and 3D data processing, Surface modeling for 3-D scenes
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Social Sciences(all)
- Communication
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2007 3DTV Conference. ed. / Georgios Triantafyllidis. 2007. 4379456 (Proceedings of 3DTV-CON).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A Framework for Scene-Flow Driven Creation of Time-Consistent Dynamic 3D Objects using Mesh Parametrizations
AU - Klie, Patrick
AU - Okon, Eugen
AU - Stefanoski, Nikolče
AU - Ostermann, Jörn
PY - 2007
Y1 - 2007
N2 - In this paper we propose a novel method to create dynamic mesh sequences with fixed connectivity from multiple camera video streams. Fixed connectivity is useful for dynamic mesh coding as mesh connectivity has to be transmitted only once and not frame-wise. The proposed method runs automatically. It deploys mesh parametrizations and voronoi diagrams from the computer graphics realm as well as 2D optical and 3D scene flow from computer vision. Assuming that a given dynamic mesh sequence does not necessarily have constant connectivity, motion estimation is performed by applying a 3D motion field to a static reconstruction in one frame. Afterwards, mesh connectivity is transferred patch-wise from one frame to the next one using remeshing techniques. The entire method is independent of static mesh resolution, hence supplying a basis for dynamic mesh coding and simplification.
AB - In this paper we propose a novel method to create dynamic mesh sequences with fixed connectivity from multiple camera video streams. Fixed connectivity is useful for dynamic mesh coding as mesh connectivity has to be transmitted only once and not frame-wise. The proposed method runs automatically. It deploys mesh parametrizations and voronoi diagrams from the computer graphics realm as well as 2D optical and 3D scene flow from computer vision. Assuming that a given dynamic mesh sequence does not necessarily have constant connectivity, motion estimation is performed by applying a 3D motion field to a static reconstruction in one frame. Afterwards, mesh connectivity is transferred patch-wise from one frame to the next one using remeshing techniques. The entire method is independent of static mesh resolution, hence supplying a basis for dynamic mesh coding and simplification.
KW - 3D mesh representation
KW - 3D motion analysis and tracking
KW - 3D motion animation
KW - Multi-view image and 3D data processing
KW - Surface modeling for 3-D scenes
UR - http://www.scopus.com/inward/record.url?scp=47949130426&partnerID=8YFLogxK
U2 - 10.1109/3DTV.2007.4379456
DO - 10.1109/3DTV.2007.4379456
M3 - Conference contribution
AN - SCOPUS:47949130426
SN - 1424407222
SN - 9781424407224
T3 - Proceedings of 3DTV-CON
BT - 2007 3DTV Conference
A2 - Triantafyllidis, Georgios
T2 - 1st International Conference on 3DTV, 3DTV-CON 2007
Y2 - 7 May 2007 through 9 May 2007
ER -