Best view selection of 3D models based on unsupervised feature learning and discrimination ability

Authors:
Chenxi Li;Zhengxing Sun;Mofei Song;Yejia Zhang
Affiliations:
Nanjing University, Nanjing, Jiangsu, China;Nanjing University, Nanjing, Jiangsu, China;Nanjing University, Nanjing, Jiangsu, China;Nanjing University, Nanjing, Jiangsu, China
Venue:
Proceedings of the 6th International Symposium on Visual Information Communication and Interaction
Year:
2013

Citing 2
Cited 0

The Princeton Shape Benchmark

SMI '04 Proceedings of the Shape Modeling International 2004
Semantics-driven approach for automatic selection of best views of 3D shapes

EG 3DOR'10 Proceedings of the 3rd Eurographics conference on 3D Object Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this poster, an approach for best view selection of 3D models is proposed, which is based on the framework that formulates the selection as a problem of evaluating views' discrimination ability. Firstly, different views' features are extracted by unsupervised feature learning. Then classifiers are trained to evaluate each view's discrimination ability. A view with the best classifier has the best discrimination ability, and it is chosen as the best view of the 3D model. At last, experiments show that 3D models of same class have similar best views.