ACM Home Page
Please provide us with feedback. Feedback
Proscenium: a framework for spatio-temporal video editing
Full text PdfPdf (2.86 MB)
Source International Multimedia Conference archive
Proceedings of the eleventh ACM international conference on Multimedia table of contents
Berkeley, CA, USA
SESSION: Student best paper contest table of contents
Pages: 177 - 184  
Year of Publication: 2003
ISBN:1-58113-722-2
Authors
Eric P. Bennett  University of North Carolina at Chapel Hill
Leonard McMillan  University of North Carolina at Chapel Hill
Sponsors
SIGMULTIMEDIA: ACM Special Interest Group on Multimedia
SIGCOMM: ACM Special Interest Group on Data Communication
ACM: Association for Computing Machinery
SIGGRAPH: ACM Special Interest Group on Computer Graphics and Interactive Techniques
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 3,   Downloads (12 Months): 62,   Citation Count: 8
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/957013.957049
What is a DOI?

ABSTRACT

We present an approach to video editing where movie sequences are treated as spatio-temporal volumes that can be sheered and warped under user control. This simple capability enables new video editing operations that support complex postproduction modifications, such as object removal and/or changes in camera motion. Our methods do not rely on complicated and error-prone image analysis or computer vision methods. Moreover, they facilitate an editing approach to video that is similar to standard image-editing tasks. Central to our system is a movie representation framework called Proscenium that supports efficient queries and operations on spatio-temporal volumes while maintaining the original source content. We have adopted a graph-based lazy-evaluation model in order to support interactive visualizations, complex data modifications, and efficient processing of large spatio-temporal volumes.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
Adobe After Effects 5.5. Adobe Systems Inc.http://www.adobe.com.
 
2
Adobe Photoshop 7.0. Adobe Systems Inc. http://www.adobe.com.
 
3
Adobe Premiere 6.5. Adobe Systems Inc. http://www.adobe.com.
 
4
Alias|Wavefront Maya 4.5. Alias|Wavefront. http://www.alias.com.
 
5
Apple Final Cut Pro 3. Apple Computer, Inc, http://www.apple.com.
 
6
Apple QuickTime 6. Apple Computer, Inc, http://www.apple.com.
 
7
Avid Media Composer. Avid Technology, Inc, http://www.avid.com.
 
8
AVS/Express 6.0, Advanced Visual Systems, Inc, http://www.avs.com.
 
9
Bolles, R.C., Baker, H.H., and Marimont, D.H. Epipolar-Plane Image Analysis: An Approach to Determining Structure from Motion. International Journal of Computer Vision, 1, 1, pp. 7--55, 1987.
 
10
Buehler, C., Bosse, M., and McMillan, L., Non-Metric Image-Based Rendering for Video Stabilization. In Proceedings of CVPR 2001, pp. 609--614, 2001.
11
12
 
13
 
14
Klein, A., Sloan, P.P., Finkelstein, A., and Cohen, M.F. Video Cubism, Microsoft Research Technical Report MSR-TR-2001-45, 2001.
15
 
16
Mayer-Patel, K. and Rowe, L.A. Design and Performance of the Berkeley Continuous Media Toolkit, Multimedia Computing and Networking 1997, Proc. SPIE 3020, pp. 194--206, 1997.
 
17
Microsoft DirectShow (DirectX 9.0). Microsoft Corporation, http://www.microsoft.com/directx.
18
 
19
 
20
 
21
Wang, J.Y.A. and Adelson, E.A. Layered Representation for Motion Analysis. In Proceedings of CVPR93, pp. 361--366, 1993.
 
22
23

CITED BY  8

Collaborative Colleagues:
Eric P. Bennett: colleagues
Leonard McMillan: colleagues