Multi-View AAM Fitting and Construction.
Multi-View AAM Fitting and Construction.
复制标题
多视图 AAM 装配和施工。
DOI：
10.1007/s11263-007-0050-3
复制
发表时间：
2008
影响因子：
19.5
通讯作者：
Kanade,Takeo
中科院分区：
文献类型：
--
作者：
Ramnath,Krishnan;Koterba,Seth;Xiao,Jing;Hu,Changbo;Matthews,Iain;Baker,Simon;Cohn,Jeffrey;Kanade,Takeo
主动外观模型（AAM）是生成的参数模型，其在过去已成功地用于对诸如人脸的可变形对象进行建模。最初的AAM配方是2D的，但它们最近被扩展到包括3D形状模型。存在各种单视图算法用于拟合和构建3D AAM，但尚未研究的一个领域是多视图算法。在本文中，我们提出了多视图算法拟合和构建3D AAM。拟合AAM到图像包括最小化输入图像和最接近的模型实例之间的误差，即解决一个非线性优化问题。在本文的第一部分中，我们描述了一个算法，用于拟合一个单一的AAM多个图像，同时捕获的相机与任意位置，旋转和响应函数。该算法采用了前人提出的缩放正射成像模型，在拟合过程中计算或标定缩放正射相机矩阵。在本文的第二部分中，我们描述了该算法的扩展，以校准每个相机的弱透视（或全透视）相机模型。本质上，我们使用人脸作为（非刚性）校准网格。我们证明，该算法的性能大致相当于使用校准网格的标准算法。本文的第三部分介绍了摄像机标定如何提高AAM拟合的性能，提出了多种单视图和多视图的非刚性运动恢复结构算法，用于构建二维AAM的相应三维非刚性形状模型。在本文的最后一部分，我们表明，使用非刚性的结构从运动构造一个3D人脸模型遭受的浅浮雕歧义，并可能导致“缩放”（拉伸/压缩）模型。我们概述了一个强大的非刚性运动立体算法校准的多视图3D AAM建设，并显示如何使用校准的多视图运动立体可以消除Bas-Relief模糊性和产量的人脸模型具有更高的3D保真度。
Active Appearance Models (AAMs) are generative, parametric models that have been successfully used in the past to model deformable objects such as human faces. 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 we 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 we 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. In the second part of the paper we describe an extension of this algorithm to calibrate weak perspective (or full perspective) camera models for each of the cameras. In essence, we use the human face as a (non-rigid) calibration grid. We 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, we 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, we 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. We 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.
登录
查看更多内容
影响因子：
19.5
作者：
Michael Jones;T. Poggio
通讯作者：
Michael Jones;T. Poggio
从运动中塑造结构中的模糊性
DOI：
10.1109/34.589211
发表时间：
1996
期刊：
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
影响因子：
--
作者：
R. Szeliski;S. B. Kang
通讯作者：
S. B. Kang
使用 3D 形状模型扩展 AAM，用于面部形状跟踪
DOI：
10.1109/icip.2004.1421835
发表时间：
2004
期刊：
2004 International Conference on Image Processing, 2004. ICIP '04.
影响因子：
--
作者：
Jaewon Sung;Daijin Kim
通讯作者：
Daijin Kim
登记。
DOI：
10.1007/978-1-4939-7647-8_1
发表时间：
2018
期刊：
Neuromethods
影响因子：
--
作者：
Joshi,AnandA
通讯作者：
Joshi,AnandA
来自未校准相机的灵活 3D 模型
影响因子：
8.8
作者：
Tim Cootes;E. D. Mauro;C. Taylor;A. Lanitis
通讯作者：
A. Lanitis