U.S. flag

An official website of the United States government, Department of Justice.

Multi-view AAM fitting and construction

NCJ Number
306110
Date Published
2008
Length
22 pages
Annotation

This paper presents multi-view algorithms for both fitting and constructing 3D active appearance models (AAMs), which are generative, parametric models that have been successfully used in the past to model deformable objects such as human faces.

Abstract

The original AAMs’ formulation was 2D, but they have recently been extended to include a 3D shape model. A variety of single-view algorithms exist for fitting and constructing 3D AAMs but one area that has not been studied is multi-view algorithms. In this paper the authors present multi-view algorithms for both fitting and constructing 3D AAMs. Fitting an AAM to an image consists of minimizing the error between the input image and the closest model instance, i.e., solving a nonlinear optimization problem. In the first part of the paper, the authors describe an algorithm for fitting a single AAM to multiple images, captured simultaneously by cameras with arbitrary locations, rotations, and response functions. This algorithm uses the scaled orthographic imaging model used by previous authors, and in the process of fitting computes, or calibrates, the scaled orthographic camera matrices. The second part of the paper describes an extension of this algorithm to calibrate weak perspective (or full perspective) camera models for each of the cameras. In essence, the authors use the human face as a (non-rigid) calibration grid. They demonstrate that the performance of this algorithm is roughly comparable to a standard algorithm using a calibration grid. In the third part of the paper, the authors show how camera calibration improves the performance of AAM fitting. A variety of non-rigid structure-from-motion algorithms, both single-view and multi-view, have been proposed that can be used to construct the corresponding 3D non-rigid shape models of a 2D AAM. In the final part of the paper, the authors show that constructing a 3D face model using non-rigid structure-from-motion suffers from the Bas-Relief ambiguity and may result in a “scaled” (stretched/compressed) model. They outline a robust non-rigid motion-stereo algorithm for calibrated multi-view 3D AAM construction and show how using calibrated multi-view motion-stereo can eliminate the Bas-Relief ambiguity and yield face models with higher 3D fidelity. (Published abstract provided)

Date Published: January 1, 2008