Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/88224
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Shared shape spaces |
Author: | Prisacariu, V. Reid, I. |
Citation: | Proceedings / IEEE International Conference on Computer Vision. IEEE International Conference on Computer Vision, 2011, pp.2587-2594 |
Publisher: | IEEE |
Publisher Place: | USA |
Issue Date: | 2011 |
Series/Report no.: | IEEE International Conference on Computer Vision |
ISBN: | 9781457711015 |
ISSN: | 1550-5499 |
Conference Name: | 2011 IEEE International Conference on Computer Vision (ICCV) (6 Nov 2011 - 13 Nov 2011 : Barcelona, Spain) |
Statement of Responsibility: | Victor Adrian Prisacariu, Ian Reid |
Abstract: | We propose a method for simultaneous shape-constrained segmentation and parameter recovery. The parameters can describe anything from 3D shape to 3D pose and we place no restriction on the topology of the shapes, i.e. they can have holes or be made of multiple parts. We use Shared Gaussian Process Latent Variable Models to learn multimodal shape-parameter spaces. These allow non-linear embeddings of the high-dimensional shape and parameter spaces in low dimensional spaces in a fully probabilistic manner. We propose a method for exploring the multimodality in the joint space in an efficient manner, by learning a mapping from the latent space to a space that encodes the similarity between shapes. We further extend the SGP-LVM to a model that makes use of a hierarchy of embeddings and show that this yields faster convergence and greater accuracy over the standard non-hierarchical embedding. Shapes are represented implicitly using level sets, and inference is made tractable by compressing the level set embedding functions with discrete cosine transforms. We show state of the art results in various fields, ranging from pose recovery to gaze tracking and to monocular 3D reconstruction. |
Rights: | ©2011 IEEE |
DOI: | 10.1109/ICCV.2011.6126547 |
Published version: | http://dx.doi.org/10.1109/iccv.2011.6126547 |
Appears in Collections: | Aurora harvest 7 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_88224.pdf Restricted Access | Restricted Access | 1.95 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.