Automatic Blending of Multiple Perspective Views for Aesthetic Composition
Hand-drawn pictures differ from ordinary perspective images in that the entire scene is composed of local feature regions each of which is projected individually as seen from its own vista point. This type of projection, called nonperspective projection, has served as one of the common media for our visual communication while its automatic generation process still needs more research. This paper presents an approach to automatically generating aesthetic nonperspective images by simulating the deformation principles seen in such hand-drawn pictures. The proposed approach first locates the optimal viewpoint for each feature region by maximizing the associated viewpoint entropy value. These optimal viewpoints are then incorporated into the 3D field of camera parameters, which is represented by regular grid samples in the 3D scene space. Finally, the camera parameters are smoothed out in order to eliminate any unexpected discontinuities between neighboring feature regions, by taking advantage of image restoration techniques. Several nonperspective images are generated to demonstrate the applicability of the proposed approach.
KeywordsMonte Carlo Sampling Camera Parameter Grid Sample Representative Object Mesh Vertex
Unable to display preview. Download preview PDF.
- 1.Agrawala, M., Zorin, D., Munzner, T.: Artistic multiprojection rendering. In: Eurographics Rendering Workshop 2000, pp. 125–136 (2000)Google Scholar
- 3.Singh, K.: A fresh perspective. In: Proceedings of Graphics Interface 2002, pp. 17–24 (2002)Google Scholar
- 4.Coleman, P., Singh, K., Barrett, L., Sudarsanam, N., Grimm, C.: 3D scene-space widgets for non-linear projection. In: Proceedings of GRAPHITE 2005, pp. 221–228 (2005)Google Scholar
- 5.Rademacher, P.: View-dependent geometry. In: Proceedings of SIGGRAPH 1999, pp. 439–446 (1999)Google Scholar
- 6.Martín, D., García, S., Torres, J.C.: Observer dependent deformations in illustration. In: Proceedings of the 1st International Symposium on Non-Photorealistic Animation and Rendering (NPAR 2000), pp. 75–82 (2000)Google Scholar
- 9.Vázquez, P.-P., Feixas, M., Sbert, M., Heidrich, W.: Viewpoint selection using view entropy. In: Proceedings of Vision Modeling and Visualization Conference (VMV 2001), pp. 273–280 (2001)Google Scholar
- 12.Sokolov, D., Plemenos, D., Tamine, K.: Viewpoint quality and global scene exploration strategies. In: Proceedings of International Conference on Computer Graphics Theory and Applications (GRAPP 2006), pp. 184–191 (2006)Google Scholar
- 13.Mühler, K., Neugebauer, M., Tietjen, C., Preim, B.: Viewpoint selection for intervention planning. In: Proceedings of Eurographics/IEEE-VGTC Symposium on Visualization, pp. 267–274 (2007)Google Scholar
- 15.Geman, D.: Random fields and inverse problems in imaging. In: Y. Vardi, M. (ed.) CAV 1998. LNCS, vol. 1427, pp. 113–193. Springer, Heidelberg (1998)Google Scholar