On Modelling Nonlinear Shape-and-Texture Appearance Manifolds

Authors:
C. Mario Christoudias;Trevor Darrell
Affiliations:
Massachusetts Institute of Technology;Massachusetts Institute of Technology
Venue:
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Year:
2005

Citing 0
Cited 13

Non-parametric and light-field deformable models

Computer Vision and Image Understanding
Robust facial feature tracking under varying face pose and facial expression

Pattern Recognition
Fast Simplex Optimization for Active Appearance Model

PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
Construction of Appearance Manifold with Embedded View-Dependent Covariance Matrix for 3D Object Recognition

IEICE - Transactions on Information and Systems
Coupled Visual and Kinematic Manifold Models for Tracking

International Journal of Computer Vision
A review of active appearance models

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Tracking and classifying of human motions with Gaussian process annealed particle filter

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Using Gaussian processes for human tracking and action classification

ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part I
Adapted active appearance models

Journal on Image and Video Processing
Manifold topological multi-resolution analysis method

Pattern Recognition
A tree-structured model of visual appearance applied to gaze tracking

ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Manifold estimation in view-based feature space for face synthesis across poses

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
Editor's choice article: Homeomorphic Manifold Analysis (HMA): Generalized separation of style and content on manifolds

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Statistical shape-and-texture appearance models employ image metamorphosis to form a rich, compact representation of object appearance. They achieve their efficiency by decomposing appearance into simpler shape-and-texture representations. In general, the shape and texture of an object can vary nonlinearly and in this case the conventional shape-and-texture mappings using Principle Component Analysis (PCA) may poorly approximate the true space. In this paper we propose two nonlinear techniques for modelling shape-and-texture appearance manifolds. Our first method uses a mixture of Gaussians in image space to separate the different parts of the shape and texture spaces. A linear shape-and-texture model is defined at each component to form the overall model. Our second approach employs a nearest-neighbor method to find a local set of shapes and images that can be morphed to explain a new input. We test each approach using a speaking-mouth video sequence and compare both approaches to a conventional Active Appearance Model (AAM).