Title
Improving the Efficiency of Viewpoint Composition
Abstract
In this paper, we concentrate on the problem of finding the viewpoint that best satisfies a set of visual composition properties, often referred to as Virtual Camera or Viewpoint Composition. Previous approaches in the literature, which are based on general optimization solvers, are limited in their practical applicability because of unsuitable computation times and limited experimental analysis. To bring performances much closer to the needs of interactive applications, we introduce novel ways to define visual properties, evaluate their satisfaction, and initialize the search for optimal viewpoints, and test them in several problems under various time budgets, quantifying also, for the first time in the domain, the importance of tuning the parameters that control the behavior of the solving process. While our solver, as others in the literature, is based on Particle Swarm Optimization, our contributions could be applied to any stochastic search process that solves through many viewpoint evaluations, such as the genetic algorithms employed by other papers in the literature. The complete source code of our approach, together with the scenes and problems we have employed, can be downloaded from https://bitbucket.org/rranon/smart-viewpoint-computation-lib.
Year
DOI
Venue
2014
10.1109/TVCG.2013.2297932
IEEE Transactions on Visualization and Computer Graphics
Keywords
Field
DocType
viewpoint computation,virtual camera,virtual camera composition,particle swarm optimisation,computer graphics,visual composition properties,virtual camera control,viewpoint composition,genetic algorithms,stochastic search process,interactive applications,particle swarm optimization,cognition,accuracy,visualization,tv
Particle swarm optimization,Computer vision,Source code,Visualization,Computer science,Viewpoints,Theoretical computer science,Artificial intelligence,Solver,Computer graphics,Genetic algorithm,Computation
Journal
Volume
Issue
ISSN
20
5
1077-2626
Citations 
PageRank 
References 
12
0.70
17
Authors
2
Name
Order
Citations
PageRank
Roberto Ranon139233.19
Tommaso Urli2798.66