Viewpoint Selection using Viewpoint Entropy

TLDR

Computing good viewpoints is crucial across fields such as computational geometry, robotics, and computer graphics, where the lack of a consensus definition makes viewpoint quality intuitively tied to the amount of scene information it conveys. The authors introduce viewpoint entropy, an information‑theoretic measure that automatically identifies optimal viewing positions and can be used to select informative view sets for scene understanding. They develop an algorithm that applies viewpoint entropy to automatically explore objects or scenes, leveraging information theory to compute optimal viewpoints.

Abstract

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.