Manifold-based constraints for operations in face space
Manifold-based constraints for operations in face space
复制标题
DOI：
10.1016/j.patcog.2015.10.003
复制
发表时间：
2016-04
期刊：
影响因子：
--
通讯作者：
Ankur Patel;W. Smith
中科院分区：
文献类型：
--
作者：
Ankur Patel;W. Smith
在本文中，我们在线性统计模型的参数空间中将面约束为流形上的点。流形是具有最大可能显著性的面的子空间，不同的点对应于唯一的恒等。我们为所选择的流形提供了详细的经验验证。我们展示了如何使用超球面流形的对数和指数映射来替换线性操作，如扭曲和平均与该流形上的操作。最后，我们使用流形开发了一种新的方法来拟合统计脸型模型到数据，该方法既鲁棒（避免过拟合）又克服了模型优势（不受接近平均值的局部最小值的影响）。我们提供了使用两个不同的目标函数（一个欠约束和一个具有许多局部最小值）拟合密集3D可变形面部模型的实验结果。在使用巴塞尔人脸模型拟合时，我们的方法优于基于BFGS准牛顿方法和Levenberg-Marquardt算法的一般非线性优化器。
In this paper, we constrain faces to points on a manifold within the parameter space of a linear statistical model. The manifold is the subspace of faces which have maximally likely distinctiveness and different points correspond to unique identities. We provide a detailed empirical validation for the chosen manifold. We show how the Log and Exponential maps for a hyperspherical manifold can be used to replace linear operations such as warping and averaging with operations on this manifold. Finally, we use the manifold to develop a new method for fitting a statistical face shape model to data, which is both robust (avoids overfitting) and overcomes model dominance (is not susceptible to local minima close to the mean face). We provide experimental results for fitting a dense 3D morphable face model to data using two different objective functions (one underconstrained and one with many local minima). Our method outperforms generic nonlinear optimisers based on the BFGS Quasi-Newton method and the Levenberg–Marquardt algorithm when fitting using the Basel Face Model.