In this paper we describe a new formulation for the 3D salient local features based on the voxel grid inspired by the Scale Invariant Feature Transform (SIFT). We use it to identify the salient keypoints (invariant points) on a 3D voxelized model and calculate invariant 3D local feature descriptors at these keypoints. We then use the bag of words approach on the 3D local features to represent the 3D models for shape retrieval. The advantages of the method are that it can be applied to rigid as well as to articulated and deformable 3D models. Finally, this approach is applied for 3D Shape Retrieval on the McGill articulated shape benchmark and then the retrieval results are presented and compared to other methods.
SPIE Symposium Electronic Imaging
January 23-27, 2011
San Francisco , CA
IS&T / SPIE 3D Image Processing and Applications
3D model retrieval, voxel grid, non-rigid 3D Model retrieval, bag of words approach, Scale Invariant Feature Transform (SIFT)