Abstract
A conventional pinhole camera captures only a small fraction of a 3-D scene due to occlusions. We introduce the graph camera, a non-pinhole with rays that circumvent occluders to create a single layer image that shows simultaneously several regions of interest in a 3-D scene. The graph camera image exhibits good continuity and little redundancy. The graph camera model is literally a graph of tens of planar pinhole cameras. A fast projection operation allows rendering in feed-forward fashion, at interactive rates, which provides support for dynamic scenes. The graph camera is an infrastructure level tool with many applications. We explore the graph camera benefits in the contexts of virtual 3-D scene exploration and summarization, and in the context of real-world 3-D scene visualization. The graph camera allows integrating multiple video feeds seamlessly, which enables monitoring complex real-world spaces with a single image.
- Agrawala, M., Zorin, D., and Munzner, T. 2000. Artistic Multiprojection Rendering. EG Workshop on Rendering Techniques 2000, 125--136. Google ScholarDigital Library
- Agarwala, A. et al., 2006. Photographing long scenes with multi-viewpoint panoram. SIGGRAPH 2006, 853--861. Google ScholarDigital Library
- Chen, E. QuickTime VR. SIGGRAPH '95, 29--38. Google ScholarDigital Library
- Diepstraten, J., Weiskopf, D., and Ertl, T., 2002. Transparency in interactive technical illustrations. Computer Graphics Forum, 21(3):317--325.Google ScholarCross Ref
- Diepstraten, J., Weiskopf, D., and Ertl, T., 2003. Interactive cutaway rendering. EUROGRAPHICS 2003, 523--532.Google Scholar
- Elmqvist, N., 2005. BalloonProbe: Reducing Occlusion in 3D using Interactive Space Distortion. ACM Symposium on Virtual Reality Software and Technology 2005, 134--137. Google ScholarDigital Library
- Furnas, G. W, 1986. Generalized fisheye views. ACM CHI'86 Conference on Human Factors in Computer Syst., 16--23. Google ScholarDigital Library
- Gortler, S. J., Grzeszczuk, R., Szeliski, R., and Cohen, M. F. 1996. The lumigraph. SIGGRAPH '96, 43--54. Google ScholarDigital Library
- Klein, A. W., Sloan, P. J., Finkelstein, A., and Cohen, M. F. 2002. Stylized video cubes. Siggraph/Eurographics Symposium on Computer Animation SCA '02, 15--22. Google ScholarDigital Library
- Kuthirummal S. and Nayar S. Multiview Radial Catadioptric Imaging for Scene Capture. SIGGRAPH '06. Google ScholarDigital Library
- Lamping, J., and Rao, R., 1996. The Hyperbolic Browser: A focus + context technique for visualizing large hierarchies. Journal of Visual Languages and Computing, 7(1):33--35.Google ScholarCross Ref
- Levoy, M. and Hanrahan, P. 1996. Light field rendering. SIGGRAPH '96, 31--42. Google ScholarDigital Library
- Mei, C., Popescu, V., and Sacks, E. 2005. The Occlusion Camera. Eurographics 2005, 335--342.Google Scholar
- Nomura, Y., L. Zhang, and S. Nayar 2007. Scene collages and flexible camera arrays. EG Symp. on Rendering, 2007. Google ScholarDigital Library
- Ponce, J. 2009. What is a camera. IEEE Conference on Computer Vision and Pattern Recognition, 2009.Google ScholarCross Ref
- Popescu, V., Aliaga, D. 2006. The depth discontinuity occlusion camera. ACM Symp. on Interactive 3-D Graphics, 139--143. Google ScholarDigital Library
- Rademacher, P. and Bishop, G. 1998. Multiple-center-of-projection images. SIGGRAPH '98, 199--206. Google ScholarDigital Library
- Roman, A., Garg, G., and Levoy, M. 2004. Interactive Design of Multi-Perspective Images for Visualizing Urban Landscapes. Visualization '04, 537--544. Google ScholarDigital Library
- Roman, A., Lensch, H. P. A. 2006. Automatic Multiperspective Images. Eurogr. Symposium on Rendering, 537--544. Google ScholarDigital Library
- Rosen, P., and Popescu, V. 2008. The epipolar occlusion camera. ACM Symp. on Interactive 3-D Graphics, 2008, 115--122. Google ScholarDigital Library
- Seitz, S. M. and Kim, J. 2003. Multiperspective Imaging. IEEE Comput. Graph. Appl. 23, 6 (Nov. 2003), 16--19. Google ScholarDigital Library
- Shade, J., Gortler, S., He, L., and Szeliski, R. 1998. Layered depth images. SIGGRAPH '98, 231--242. Google ScholarDigital Library
- Szeliski, R., and Shum, H.-Y. 1997. Full view panoramic image mosaics and texture-mapped models. SIGG '97, 251--258. Google ScholarDigital Library
- Wong N., Carpendale, M. S. T., and Greenberg, S., 2003. EdgeLens: An interactive method for managing edge congestion in graphs. IEEE Symp. on Info. Vis. 2003, 51--58. Google ScholarDigital Library
- Wood, D. N., Finkelstein, A., Hughes, J. F., Thayer, C. E., and Salesin, D. H. 1997. Multiperspective panoramas for cel animation. SIGGRAPH '97, 243--250. Google ScholarDigital Library
- Yu, J., and McMillan, L. 2004. General Linear Cameras European Conf. on Computer Vision 2004, Vol. 2, 14--27.Google Scholar
- Yu, J., and McMillan, L. 2004. A Framework for Multiperspective Rendering. Eurographics Symposium on Rendering 2004, 61--68. Google ScholarDigital Library
- Yu, J., and McMillan, L. 2005. Analyzing Reflections via Multiperspective Imaging. Computer Vision and Pattern Recognition (CVPR), 2005, 117--124. Google ScholarDigital Library
Index Terms
- The graph camera
Recommendations
The graph camera
SIGGRAPH Asia '09: ACM SIGGRAPH Asia 2009 papersA conventional pinhole camera captures only a small fraction of a 3-D scene due to occlusions. We introduce the graph camera, a non-pinhole with rays that circumvent occluders to create a single layer image that shows simultaneously several regions of ...
A Comprehensive and Versatile Camera Model for Cameras with Tilt Lenses
We propose camera models for cameras that are equipped with lenses that can be tilted in an arbitrary direction (often called Scheimpflug optics). The proposed models are comprehensive: they can handle all tilt lens types that are in common use for ...
A Multi-view Camera Model for Line-Scan Cameras with Telecentric Lenses
AbstractWe propose a novel multi-view camera model for line-scan cameras with telecentric lenses. The camera model supports an arbitrary number of cameras and assumes a linear relative motion with constant velocity between the cameras and the object. We ...
Comments