“Creating generative models from range images” by Ramamoorthi and Arvo

We describe a new approach for creating concise high-level generative models from range images or other approximate representations of real objects. Using data from a variety of acquisition techniques and a user-defined class of models, our method produces a compact object representation that is intuitive and easy to edit. The algorithm has two inter-related phases: recognition, which chooses an appropriate model within a user-specified hierarchy, and parameter estimation, which adjusts the model to best fit the data. Since the approach is model-based, it is relatively insensitive to noise and missing data. We describe practical heuristics for automatically making tradeoffs between simplicity and accuracy to select the best model in a given hierarchy. We also describe a general and efficient technique for optimizing a model by refining its constituent curves. We demonstrate our approach for model recovery using both real and synthetic data and several generative model hierarchies.

1. T. O. Binford. Visual perception by computer. In P1vceedings of the IEEE Conference on Systems Science and Cybernetics, 1971.
2. Jean-Yves Bouguet and Pietro Perona. 3D photography on your desk. In ICCV 98 plvceedings, pages 43-50, 1998.
3. R. A. Brooks. Model-based three-dimensional interpretations of twodimensional images. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 5(2): 140-150, 1983.
4. M.F. Cohen. Interactive spacetime control for animation. In SIGGRAPH 92 p~vceedings, pages 293-302, 1992.
5. Brian Curless and Marc Levoy. A volumetric method for building complex models from range images. In SIGGRAPH 96 plvceedings, pages 303-312, 1996.
6. Paul E. Debevec, Camillo J. Taylor, and Jitendra Malik. Modeling and rendering architecture from photographs: A hybrid geometry- and image-based approach. In SIGGRAPH 96proceedings, pages 11-20, 1996.
7. D. DeCarlo and D. Metaxas. Blended deformable models. PAMI, 18(4):443- 448, Apr 1996.
8. D. DeCarlo and D. Metaxas. Shape evolution with structural and topological changes using blending. PAMI, 20(11): 1186-1205, Nov 1998.
9. S.J. Dickinson, D. Metaxas, and A. Pentland. The role of model-based segmentation in the recovery of volume parts from range data. PAMI, 19(3):259-267, Mar 1997.
10. Matthias Eck and Hugues Hoppe. Automatic reconstruction of B-Spline surfaces of arbitrary topological type. In SIGGRAPH 96 proceedings, pages 325-334, 1996.
11. F. Ferrie, J. Lagarde, and R Whaite. Darboux frames, snakes, and super-quadrics: Geometry from the bottom up. PAMI, 15(8):771-784, 1993.
12. Hugues Hoppe, Tony DeRose, Tom Duchamp, John McDonald, and Wemer Stuetzle. Surface reconstruction from unorganized points. In SIGGRAPH 92 proceedings, pages 71-78, 1992.
13. Hugues Hoppe, Tony DeRose, Tom Duchamp, John McDonald, and Wemer Stuetzle. Mesh optimization. In SIGGRAPH 93 proceedings, pages 19-26, 1993.
14. Venkat Krishnamurthy and Marc Levoy. Fitting smooth surfaces to dense polygon meshes. In SIGGRAPH 96 plvceedings, pages 313-324, 1996.
15. R. Nevatia. Structured Descriptions of Complex Curved Objects for Recognition and Visual Memory. PhD thesis, Stanford, 1974.
16. A. Pentland. Toward an ideal 3-D CAD system. In P1vc. SPIE Conf. Machine Vision Man-Machine Intelface, 1987. San Diego, CA.
17. Michael Plass and Maureen Stone. Curve-fitting with piecewise parametric cubics. In SIGGRAPH 83 plvceedings, pages 229-239, 1983.
18. W. Press, S. Teukolsky, W. Vetterling, and R Flannery. NumericaI Recipes in C: The Art of Scientific Computing (2nd ed.). Cambridge University Press, 1992.
19. N. Sriranga Raja and A. K. Jain. Obtaining generic parts from range images using a multi-view representation. Computer Vision, Graphics, and Image Processing. Image Understanding, 60(1):44-64, July 1994.
20. R. Ramamoorthi and A. H. Barr. Fast construction of accurate quatemion splines. In SIGGRAPH 97proceedings, pages 287-292, 1997.
21. J. Snyder. Generative Modeling for Computer Graphics and CAD. Academic Press, 1992.
22. John M. Snyder and James T. Kajiya. Generative modeling: A symbolic system for geometric modeling. In SIGGRAPH 92 p~vceedings, pages 369-378, 1992.
23. F. Solina and R. Bajcsy. Recovery of Parametric Models from Range Images: The Case for Superquadrics with Global Deformations. PAMI, 12(2): 131-147, February 1990.
24. D. Terzopoulos and D. Metaxas. Dynamic 3D models with local and global deformations: Deformable superquadrics. PAMI, 13 (7):703-714, July 1991.
25. Marjan Trobina. Error model of a coded-light range sensor. Technical Report BIWI-TR- 164, ETH, Zurich, 1995.
26. Greg Turk and Marc Levoy. Zippered polygon meshes from range images. In SIGGRAPH 94 proceedings, pages 311-318, 1994.
27. K. Wu and M. D. Levine. Recovering parametric geons from multiview range data. In CVPR, pages 159-166, June 1994.
28. D. Zwillinger. Handbook of Differential Equations. Academic Press, 1989.