Journal
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING
Volume 19, Issue 11, Pages 1397-1408Publisher
ZHEJIANG UNIV
DOI: 10.1631/FITEE.1601764
Keywords
Model retrieval; Euclidean space; Riemannian manifold; Hilbert space; Metric learning; TP391
Categories
Funding
- National Key R&D Program of China [2017YFB1002600]
- National Natural Science Foundation of China [61272304]
- Natural Science Foundation of Zhejiang Province, China [LQ16F020007, LQ17F030002]
- Natural Science Foundation of Ningbo, China [2017A610108]
Ask authors/readers for more resources
We propose a new framework for image-based three-dimensional (3D) model retrieval. We first model the query image as a Euclidean point. Then we model all projected views of a 3D model as a symmetric positive definite (SPD) matrix, which is a point on a Riemannian manifold. Thus, the image-based 3D model retrieval is reduced to a problem of Euclid-to-Riemann metric learning. To solve this heterogeneous matching problem, we map the Euclidean space and SPD Riemannian manifold to the same high-dimensional Hilbert space, thus shrinking the great gap between them. Finally, we design an optimization algorithm to learn a metric in this Hilbert space using a kernel trick. Any new image descriptors, such as the features from deep learning, can be easily embedded in our framework. Experimental results show the advantages of our approach over the state-of-the-art methods for image-based 3D model retrieval.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available