Shared shape spaces
Authors:
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 2587-2594
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.Keywords
This publication has 9 references indexed in Scilit:
- Nonlinear shape manifolds as shape priors in level set segmentation and tracking2011
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009
- Shared Kernel Information Embedding for discriminative inference2009
- Sparse probabilistic regression for activity-independent human pose inference2008
- The Joint Manifold Model for Semi-supervised Multi-valued Regression2007
- Dynamical statistical shape priors for level set-based trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Local distance preservation in the GP-LVM through back constraints2006
- 3D human pose from silhouettes by relevance vector regression2004
- A shape-based approach to the segmentation of medical imagery using level setsIEEE Transactions on Medical Imaging, 2003