Viewpoint Selection using Viewpoint Entropy

Computation of good viewpoints is important in several fields: computational geometry, visual servoing, robot motion, graph drawing, etc. In addition, selection of good views is rapidly becoming a key issue in computer graphics due to the new techniques of Image Based Rendering. Although there is no consensus about what a good view means in Computer Graphics, the quality of a viewpoint is intuitively related to how much information it gives us about a scene. In this paper we use the theoretical basis provided by Information Theory to define a new measure, viewpoint entropy, that allows us to compute good viewing positions automatically. We also show how it can be used to select a set of good views of a scene for scene understanding. Finally, we design an algorithm that uses this measure to explore automatically objects or scenes.

[1]  Richard E. Blahut,et al.  Principles and practice of information theory , 1987 .

[2]  Satoru Kawai,et al.  A simple method for computing general position in displaying three-dimensional objects , 1988, Comput. Vis. Graph. Image Process..

[3]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[4]  Leonard McMillan,et al.  Plenoptic Modeling: An Image-Based Rendering System , 2023 .

[5]  Václav Hlavác,et al.  Automatic Selection of Reference Views for Image-Based Scene Representations , 1996, ECCV.

[6]  David Salesin,et al.  The virtual cinematographer: a paradigm for automatic real-time camera control and directing , 1996, SIGGRAPH.

[7]  Gregory Dudek,et al.  Automated creation of image-based virtual reality , 1997, Other Conferences.

[8]  A. David Marshall,et al.  Viewpoint Selection for Complete Surface Coverage of Three Dimensional Objects , 1998, BMVC.

[9]  Robert B. Fisher,et al.  A Best Next View Selection Algorithm Incorporating a Quality Criterion , 1998, BMVC.

[10]  Noboru Ohnishi,et al.  Active vision system based on information theory , 1998, Systems and Computers in Japan.

[11]  Noboru Ohnishi,et al.  Active vision system based on information theory , 1998, Systems and Computers in Japan.

[12]  Frank P. Ferrie,et al.  Viewpoint selection by navigation through entropy maps , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[13]  Mateu Sbert,et al.  An Information Theory Framework for the Analysis of Scene Complexity , 1999, Comput. Graph. Forum.

[14]  Dimitri Plemenos,et al.  Scene understanding techniques using a virtual camera , 2000, Eurographics.

[15]  Nicolas Courty,et al.  Image-Based Virtual Camera Motion Strategies , 2000, Graphics Interface.

[16]  Ben J Hicks,et al.  SPIE - The International Society for Optical Engineering , 2001 .