Shape rank: efficient web3D search technique using 3D features

In recent years, usage of 3D object for various purposes, such as CG movie, games, web 3D and so on, is rapidly increasing. In addition, 3D shape capturing method is also improved and many commercial products are now widely available. As a result, a number of 3D objects those are uploaded and published on the Web will greatly increase in the near future. On the other hand, the method for retrieving 3D objects from the Web is not thoroughly researched yet. Based on this background, we propose an efficient method to retrieve a 3D object from the Web using both 3D feature of the 3D objects and ranking results of web search. In this demo, we will show a real time demo on 3D object search using a number of 3D data we scanned in our lab. and retrieved data from the Web.

[1]  Ryutarou Ohbuchi,et al.  Salient local visual features for shape-based 3D model retrieval , 2008, 2008 IEEE International Conference on Shape Modeling and Applications.

[2]  Shumeet Baluja,et al.  Pagerank for product image search , 2008, WWW.

[3]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Yuichi Yoshida,et al.  Multiclass VisualRank: image ranking method in clustered subsets based on visual features , 2009, SIGIR.

[5]  Han Wang,et al.  Real-time corner detection algorithm for motion estimation , 1995, Image Vis. Comput..

[6]  Yasuo Kuniyoshi,et al.  Partial matching of real textured 3D objects using color cubic higher-order local auto-correlation features , 2010, The Visual Computer.

[7]  Shumeet Baluja,et al.  VisualRank: Applying PageRank to Large-Scale Image Search , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Ryo Furukawa,et al.  Dense 3D Reconstruction with an Uncalibrated Stereo System using Coded Structured Light , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.