Paper Info
Title
Automatic Generation of Canonical Views for CAD Models
Abstract
Selecting the best views for 3D objects is useful for many applications. However, with the existing methods applied in CAD models, the results neither exhibit the 3D structures of the models fairly nor conform to human's browsing habits. In this paper, we present a robust method to generate the canonical views of CAD models, and the above problem is solved by considering the geometry and visual salient features simultaneously. We first demonstrate that for a CAD model, the three coordinate axes can be approximately determined by the scaled normals of its faces, such that the pose can be robustly normalized. A graph-based algorithm is also designed to accelerate the searching process. Then, a convex hull based method is applied to infer the upright orientation. Finally, four isometric views are selected as candidates, and the one whose depth image owns the most visual features is selected. Experiments on the Engineering Shape Benchmark (ESB) show that the views generated by our method are pleasant, informative and representative. We also apply our method in the calculation of model rectilinearity, and the results demonstrate its high performance.
Year
DOI
Venue
2011
10.1109/CAD/Graphics.2011.25
CAD/Graphics
Keywords
Field
DocType
model rectilinearity,automatic generation,cad models,robust method,browsing habit,cad model,visual feature,best view,visual salient,engineering shape benchmark,existing method,canonical view,canonical views,computational geometry,convex hull,graph theory,isometric view,cad
CAD,Graph theory,Graph,Computer vision,Mathematical optimization,Normalization (statistics),Computer science,Computational geometry,Convex hull,Isometric projection,Artificial intelligence,Salient
Conference
Citations 
PageRank 
References 
2
0.40
13
Authors
4
Name
Order
Citations
PageRank
Kai-Mo Hu1434.89
Bin Wang228724.47
Bin Yuan3106.32
Jun-hai Yong462061.47