Non-parametric Spectral Model for Shape Retrieval
Authors:
- Andrea GasparettoAGAndrea Gasparetto
- Giorgia MinelloGMGiorgia Minello
- Andrea TorselloATAndrea Torsello
- 1 October 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 32, 344-352
Abstract
Non-rigid 3D shape retrieval is an active and important research topic in content based object retrieval. This problem is often cast in terms of the shapes intrinsic geometry due to its invariance to a wide range of non-rigid deformations. In this paper, we devise a novel generative model for shape retrieval based on the spectral representation of the Laplacian of a mesh. Contrary to common use, our approach avoids the ubiquitous correspondence problem by transforming the eigenvectors of the Laplacian to a density in the spectral-embedding space which is estimated nonparametrically. We show that this model can efficiently be learned from a set of 3D meshes. The experimental results on the SHREC'14 benchmark show the effectiveness of the approach compared to the state-of-the-art.Keywords
This publication has 26 references indexed in Scilit:
- Supervised learning of bag‐of‐features shape descriptors using sparse codingComputer Graphics Forum, 2014
- Fine-grained semi-supervised labeling of large shape collectionsACM Transactions on Graphics, 2013
- Intrinsic spatial pyramid matching for deformable 3D shape retrievalInternational Journal of Multimedia Information Retrieval, 2013
- Learning Spectral Descriptors for Deformable Shape CorrespondenceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- A multiresolution descriptor for deformable 3D shape retrievalThe Visual Computer, 2013
- 3D Shape Classification Using Commute Time2012
- A spectral approach to shape-based retrieval of articulated 3D modelsComputer-Aided Design, 2007
- Indexing and retrieval of 3D models aided by active learning2001
- Unsupervised Learning by Probabilistic Latent Semantic AnalysisMachine Learning, 2001
- Using spin images for efficient object recognition in cluttered 3D scenesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999