Dynamic Probabilistic Volumetric Models
2013
Conference Paper
ps
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.
Author(s): | Ulusoy, Ali Osman and Biris, Octavian and Mundy, Joseph L. |
Book Title: | ICCV |
Pages: | 505-512 |
Year: | 2013 |
Department(s): | Perceiving Systems |
Bibtex Type: | Conference Paper (inproceedings) |
Paper Type: | Conference |
DOI: | 10.1109/ICCV.2013.68 |
Links: |
video
|
Video: | |
Attachments: |
pdf
|
BibTex @inproceedings{Ulusoy2013, title = {{Dynamic Probabilistic Volumetric Models}}, author = {Ulusoy, Ali Osman and Biris, Octavian and Mundy, Joseph L.}, booktitle = {ICCV}, pages = {505-512}, year = {2013}, doi = {10.1109/ICCV.2013.68} } |