2013 IEEE International Conference on Computer Vision, 2013, p.505-512
2013
Volltextzugriff (PDF)
Details
- Autor(en) / Beteiligte
- Titel
- Dynamic Probabilistic Volumetric Models
- Ist Teil von
- 2013 IEEE International Conference on Computer Vision, 2013, p.505-512
- Ort / Verlag
- IEEE
- Erscheinungsjahr
- 2013
- Quelle
- IEEE Electronic Library Online
- Beschreibungen/Notizen
- This paper presents a probabilistic volumetric framework for image based modeling of general dynamic 3-d scenes. The framework is targeted towards high quality modeling of complex scenes evolving over thousands of frames. Extensive storage and computational resources are required in processing large scale space-time (4-d) data. Existing methods typically store separate 3-d models at each time step and do not address such limitations. A novel 4-d representation is proposed that adaptively subdivides in space and time to explain the appearance of 3-d dynamic surfaces. This representation is shown to achieve compression of 4-d data and provide efficient spatio-temporal processing. The advances of the proposed framework is demonstrated on standard datasets using free-viewpoint video and 3-d tracking applications.
- Sprache
- Englisch
- Identifikatoren
- ISSN: 1550-5499eISSN: 2380-7504DOI: 10.1109/ICCV.2013.68Titel-ID: cdi_proquest_miscellaneous_1669868422
- Format
- –
- Schlagworte
- 3-d tracking, 4-d compression, Computational modeling, Computer vision, Conferences, Data compression, dynamic scene analysis, Dynamics, free viewpoint video, Graphics processing units, image based modeling, Mathematical models, Octrees, Probabilistic logic, Probabilistic methods, Probability theory, Rendering (computer graphics), Representations, Solid modeling, Tracking, Volumetric analysis