A unified information-theoretic framework for viewpoint selection and mesh saliency

ABSTRACT

Viewpoint selection is an emerging area in computer graphics with applications in fields such as scene exploration, image-based modeling, and volume visualization. In particular, best view selection algorithms are used to obtain the minimum number of views (or images) in order to understand or model an object or scene better. In this article, we present a unified framework for viewpoint selection and mesh saliency based on the definition of an information channel between a set of viewpoints (input) and the set of polygons of an object (output). The mutual information of this channel is shown to be a powerful tool to deal with viewpoint selection, viewpoint stability, object exploration and viewpoint-based saliency. In addition, viewpoint mutual information is extended using saliency as an importance factor, showing how perceptual criteria can be incorporated to our method. Although we use a sphere of viewpoints around an object, our framework is also valid for any set of viewpoints in a closed scene. A number of experiments demonstrate the robustness of our approach and the good behavior of the proposed measures.

REFERENCES

• 1: Andújar, C., Vázquez, P. P., and Fairén, M. 2004. Way-finder: Guided tours through complex walkthrough models. Computer Graphics Forum (Eurographics 2004) 23, 3, 499--508.
• 2: Blanz, V., Tarr, M., and Bülthoff, H. 1999. What object attributes determine canonical views? Perception 28, 575--599.
• 3: Bordoloi, U. D. and Shen, H.-W. 2005. Viewpoint evaluation for volume rendering. In IEEE Visualization 2005. IEEE, Los Alamitos, CA, 487--494.
• 4: Bülthoff, H., Edelman, S., and Tarr, M. 1995. How are three-dimensional objects represented in the brain? Cerebral Cortex 5, 247--260.
• 5: Burbea, J. and Rao, C. R. 1982. On the convexity of some divergence measures based on entropy functions. IEEE Trans. Inform. Theory 28, 3, 489--495.
• 6: Castelló, P., Sbert, M., Chover, M., and Feixas, M. 2007. Viewpoint entropy-driven simplification. In Proceedings of WSCG 2007. 249--256.
• 7: Christensen, P. Ambient occlusion, image-based illumination and global illumination. Photorealistic RenderMan Application Notes, Note 35.
• 8: Thomas M. Cover , Joy A. Thomas, Elements of information theory, Wiley-Interscience, New York, NY, 1991
• 9: Feixas, M. 2002. An information-theory framework for the study of the complexity of visibility and radiosity in a scene. Ph.D. thesis, Universitat Politècnica de Catalunya, Barcelona, Spain.
• 10: Ran Gal , Daniel Cohen-Or, Salient geometric features for partial shape matching and similarity, ACM Transactions on Graphics (TOG), v.25 n.1, p.130-150, January 2006 [doi>10.1145/1122501.1122507]
• 11: González-Baños, H. H. and Latombe, J.-C. 2002. Navigation strategies for exploring indoor environments. Int. J. Robotics Resear. 21, 10-11, 829--848.
• 12: Bruce Gooch , Erik Reinhard , Chris Moulding , Peter Shirley, Artistic Composition for Image Creation, Proceedings of the 12th Eurographics Workshop on Rendering Techniques, p.83-88, June 25-27, 2001
• 13: Andrey Iones , Anton Krupkin , Mateu Sbert , Sergey Zhukov, Fast, Realistic Lighting for Video Games, IEEE Computer Graphics and Applications, v.23 n.3, p.54-64, May 2003 [doi>10.1109/MCG.2003.1198263]
• 14: Itti, L. and Baldi, P. 2006. Bayesian surprise attracts human attention. In Advances in Neural Information Processing Systems, Vol. 19 (NIPS 2005). 1--8.
• 15: Laurent Itti , Christof Koch , Ernst Niebur, A Model of Saliency-Based Visual Attention for Rapid Scene Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.20 n.11, p.1254-1259, November 1998 [doi>10.1109/34.730558]
• 16: Youngmin Kim , Amitabh Varshney, Saliency-guided Enhancement for Volume Visualization, IEEE Transactions on Visualization and Computer Graphics, v.12 n.5, p.925-932, September 2006 [doi>10.1109/TVCG.2006.174]
• 17: Landis, H. 2002. RenderMan in production. In Course Notes of ACM SIGGRAPH, ACM, New York, NY.
• 18: Chang Ha Lee , Amitabh Varshney , David W. Jacobs, Mesh saliency, ACM Transactions on Graphics (TOG), v.24 n.3, July 2005
• 19: Lu, A., Maciejewski, R., and Ebert, D. S. 2006. Volume composition using eye tracking data. In Proceedings of EuroVis '06, ACM, New York, NY, 655--662.
• 20: Palmer, S., Rosch, E., and Chase, P. 1981. Canonical perspective and the perception of objects. Atten. Perform. IX, 135--151.
• 21: Plemenos, D. and Benayada, M. 1996. Intelligent display techniques in scene modeling. New techniques to automatically compute good views. In Proceedings of Graphi Con'96.
• 22: Polonsky, O., Patané, G., Biasotti, S., Gotsman, C., and Spagnuolo, M. 2005. What's in an image? Visual Computer 21, 8-10, 840--847.
• 23: Sbert, M., Plemenos, D., Feixas, M., and González, F. 2005. Viewpoint quality: Measures and applications. In Proceedings of 1st Computational Aesthetics in Graphics, Visualization and Imaging, 185--192.
• 24: Slonim, N. and Tishby, N. 1999. Agglomerative information bottleneck. In Proceedings of Neural Information Processing Systems (NIPS). MIT Press, 617--623.
• 25: Noam Slonim , Naftali Tishby, Document clustering using word clusters via the information bottleneck method, Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, p.208-215, July 24-28, 2000, Athens, Greece [doi>10.1145/345508.345578]
• 26: Sokolov, D., Plemenos, D., and Tamine, K. 2006. Methods and data structures for virtual world exploration. Visual Computer 22, 7, 506--516.
• 27: Takahashi, S., Fujishiro, I., Takeshima, Y., and Nishita, T. 2005. A feature-driven approach to locating optimal viewpoints for volume visualization. In Proceedings of IEEE Visualization 2005. IEEE, Los Alamitos, CA, 495--502.
• 28: Tarr, M., Bülthoff, H., Zabinski, M., and Blanz, V. 1997. To what extent do unique parts influence recognition across changes in viewpoint? Psychol. Science 8, 4, 282--289.
• 29: Pere-Pau Vázquez , Miquel Feixas , Mateu Sbert , Wolfgang Heidrich, Viewpoint Selection using Viewpoint Entropy, Proceedings of the Vision Modeling and Visualization Conference 2001, p.273-280, November 21-23, 2001
• 30: Vázquez, P.-P., Feixas, M., Sbert, M., and Heidrich, W. 2003. Automatic view selection using viewpoint entropy and its applications to image-based modeling. Comput. Graph. For. 22, 4, 689--700.
• 31: Vázquez, P. P., Feixas, M., Sbert, M., and Llobet, A. 2006. Realtime automatic selection of good molecular views. Comput. Graph. 30, 1, 98--110.
• 32: Ivan Viola , Miquel Feixas , Mateu Sbert , Meister Eduard Groller, Importance-Driven Focus of Attention, IEEE Transactions on Visualization and Computer Graphics, v.12 n.5, p.933-940, September 2006 [doi>10.1109/TVCG.2006.152]
• 33: Hitoshi Yamauchi , Waqar Saleem , Shin Yoshizawa , Zachi Karni , Alexander Belyaev , Hans-Peter Seidel, Towards Stable and Salient Multi-View Representation of 3D Shapes, Proceedings of the IEEE International Conference on Shape Modeling and Applications 2006, p.40, June 14-16, 2006 [doi>10.1109/SMI.2006.42]
• 34: Zhukov, S., Iones, A., and Kronin, G. 1998. An ambient light illumination model. In Proceedings of the Eurographics Workshop: Rendering Techniques. 45--56.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.7 Three-Dimensional Graphics and Realism

General Terms:
Algorithms, Experimentation, Human Factors

Keywords:
Viewpoint selection, information theory, mesh saliency, visual perception