Paper Info
Title
A benchmark for best view selection of 3D objects
Abstract
The best view selection corresponds to the task of automatically selecting the most representative view of a 3D model. In this paper, we describe a benchmark for evaluation of best view selection algorithms. The benchmark consists of the preferred views of 68 3D models provided by 26 human subjects. The data was collected using a web-based subjective experiment where the users were asked to select the most informative view of a 3D model. We provided a quantitative evaluation measure based on this ground truth data, and compared the performances of seven best view selection algorithms.
Year
DOI
Venue
2010
10.1145/1877808.1877819
3DOR@MM
Keywords
Field
DocType
best view selection corresponds,3d shape analysis,web-based subjective experiment,ground truth data,informative view,best view selection algorithm,quantitative evaluation measure,preferred view,human subject,best view selection,representative view,ground truth,shape analysis
Computer science,Ground truth,Artificial intelligence,Machine learning
Conference
Citations 
PageRank 
References 
16
0.80
10
Authors
3
Name
Order
Citations
PageRank
Helin Dutağaci117912.51
Chun Pan Cheung2843.43
Afzal Godil361930.70