Image-based 3D model retrieval using manifold learning
- 11 Downloads
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.
Key wordsModel retrieval Euclidean space Riemannian manifold Hilbert space Metric learning
Unable to display preview. Download preview PDF.
- Hamm J, Lee DD, 2009. Extended Grassmann kernels for subspace-based learning. Advances in Neural Information Processing Systems, p.601–608.Google Scholar
- Kazhdan M, Funkhouser T, Rusinkiewicz S, 2003. Rotation invariant spherical harmonic representation of 3D shape descriptors. Proc Eurographics/ACM SIGGRAPH Symp on Geometry Processing, p.156–164.Google Scholar
- Vincent P, Bengio Y, 2001. K-local hyperplane and convex distance nearest neighbor algorithms. Proc 14th Int Conf on Neural Information Processing Systems: Natural and Synthetic, p.985–992.Google Scholar