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

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche

Reference

Miquel Feixas , Mateu Sbert , Francisco González: A unified information-theoretic framework for viewpoint selection and mesh saliency. In: Computational Aesthetics 2006.

DOI

Abstract

Viewpoint selection is an emerging area in computer graphics with applications in fields such as scene under- standing, volume visualization, image-based modeling, and molecular visualization. In this paper, we present a unified framework for viewpoint selection and mesh saliency based on the definition of an information channel between a set of viewpoints and the set of polygons of an object. The mutual information of this channel is a powerful tool to deal with viewpoint selection and mesh visibility. In addition, the Jensen-Shannon divergence, closely related to mutual information, gives us a measure of viewpoint similarity and permits us to obtain the object saliency. Although we deal with the sphere of viewpoints around an object, our framework is also valid for any set of viewpoints in a closed scene. Several experiments show the robustness of the presented approach and the good behavior of the proposed measures.

Extended Abstract

Bibtex

Used References

[AVF04] A NDÚJAR C., VÁZQUEZ P. P., FAIRÉN M.: Way-finder: guided tours through complex walthrough models. Computer Graphics Forum (Eurographics 2004) (2004).

[BDP00] BARRAL P., D ORME G., P LEMENOS D.: Scene understanding techniques using a virtual camera. In Short papers proceedings, Eurographics 2000 (August 2000). Held in Interlagen, Switzerland.

[BR82] B URBEA J., R AO C. R.: On the convexity of some divergence measures based on entropy functions. IEEE Transactions on Information Theory 28, 3 (May 1982), 489–495.

[BS05] B ORDOLOI U. D., S HEN H.-W.: Viewpoint eval- uation for volume rendering. In Visualization, IEEE 2005 (May 2005), pp. 62–62.

[CT91] C OVER T. M., T HOMAS J. A.: Elements of In- formation Theory. Wiley Series in Telecommunications, 1991.

[FdABS99] F EIXAS M., DEL ACEBO E., B EKAERT P., S BERT M.: An information theory framework for the analysis of scene complexity. Computer Graphics Fo- rum (Proceedings of Eurographics’99) 18, 3 (September 1999), 95–106.

[LVJ05] L EE C. H., VARSHNEY A., JACOBS D. W.: Mesh saliency. Computer Graphics (Proceedings of SIG- GRAPH’05) (July - August 2005). Held in Los Angeles, USA.

[Ple03] P LEMENOS D.: Exploring virtual worlds: Current techniques and future issues. In International Conference GraphiCon’2003 (September 2003). Held in Moscow, Russia.

[SPFG05] S BERT M., P LEMENOS D., F EIXAS M., G ONZÁLEZ F.: Viewpoint quality: Measures and appli- cations. In Proceedings of 1st Computational Aesthetics in Graphics, Visualization and Imaging (May 2005). Held in Girona, Spain.

[ST00a] S LONIM N., T ISHBY N.: Agglomerative infor- mation bottleneck. In Proceedings of NIPS-12 (Neu- ral Information Processing Systems) (2000), MIT Press, pp. 617–623.

[ST00b] S LONIM N., T ISHBY N.: Document cluster- ing using word clusters via the information bottleneck method. In Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (2000), ACM Press, pp. 208–215. Held in Athens, Greece.

[TFTN05] TAKAHASHI S., F UJISHIRO I., TAKESHIMA Y., N ISHITA T.: Locating optimal viewpoints for volume visualization. In Visualization, IEEE 2005 (May 2005).

[TPB99] T ISHBY N., P EREIRA F. C., B IALEK W.: The information bottleneck method. In Proceedings of the 37th Annual Allerton Conference on Communication, Control and Computing (1999), pp. 368–377.

[VFSH01] VÁZQUEZ P. P., F EIXAS M., S BERT M., H EI - DRICH W.: Viewpoint selection using viewpoint entropy. In Proceedings of Vision, Modeling, and Visualization 2001 (Stuttgart, Germany, November 2001), Ertl T., Girod B., Greiner G., Niemann H.„ Seidel H.-P., (Eds.), pp. 273– 280. Held in Stuttgart, Germany.

[VFSH03] VÁZQUEZ P. P., F EIXAS M., S BERT M., H EI - DRICH W.: Automatic view selection using viewpoint en- tropy and its application to image-based modeling. Com- puter Graphics Forum (Desember 2003).

[VFSL02] VÁZQUEZ P. P., F EIXAS M., S BERT M., L LO - BET A.: A new tool for obtaining good views for molecules. In Proceedings of VisSym’02 (Eurographics- IEEE TCVG Symposium on Visualization) (May 2002), Ebert D., Brunet P.„ Navazo I., (Eds.), pp. 0–1. Held in Barcelona, Spain.

[VS03] VÁZQUEZ P. P., S BERT M.: Automatic indoor scene exploration. In Interantional Conference on Artifi- cial Intelligence and Computer Graphics, 3IA (Limoges, France, may 2003). Held in Limoges, France.

Links

Full Text

http://www.researchgate.net/publication/220245081_A_unified_information-theoretic_framework_for_viewpoint_selection_and_mesh_saliency/links/0912f510865711a631000000

http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.77.4610&rep=rep1&type=pdf

intern file

Sonstige Links