Enhanced 2D/3D Approaches Based on Relevance Index for 3D-Shape Retrieval

Abstract : We present a new approach for 3D model indexing and retrieval using 2D/3D shape descriptors based on silhouettes or depth-buffer images. To take into account the dispersion of information in the views, we associate to each view a relevance index which will be afterward used in the dissimilarity computation. The performance of this new approach is evaluated on the Princeton 3D Shape Benchmark database.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.inria.fr/hal-00802602
Contributor : Anne Verroust-Blondet <>
Submitted on : Wednesday, March 20, 2013 - 10:41:36 AM
Last modification on : Friday, May 25, 2018 - 12:02:03 PM
Long-term archiving on : Friday, June 21, 2013 - 4:13:02 AM

File

chaouchverroustblondetsmi06.pd...
Files produced by the author(s)

Identifiers

Collections

Citation

Mohamed Chaouch, Anne Verroust-Blondet. Enhanced 2D/3D Approaches Based on Relevance Index for 3D-Shape Retrieval. SMI 2006 - International Conference on Shape Modeling and Applications, Jun 2006, Matsushima, Japan. ⟨10.1109/SMI.2006.11⟩. ⟨hal-00802602⟩

Share

Metrics

Record views

187

Files downloads

209