arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1612.09548cs.CV
收藏

基于张量的统一主动外观人脸模型

A Unified Tensor-based Active Appearance Face Model

Zhen-Hua Feng, Josef Kittler, William Christmas, Xiao-Jun Wu

摘要:

人脸的外貌变化给人脸图像分析带来了很多困难。为了应对这一挑战,我们提出了一个统一的基于张量的主动外观模型(UT-AAM),用于联合建模的几何和纹理信息的二维人脸。对于每种类型的人脸信息,即形状和纹理,我们构建了一个统一的张量模型捕捉所有相关的外观变化。这与经典张量AAM的变分特定模型形成对比。为了实现姿态变化的统一,提出了一种处理自遮挡人脸的策略,以获得一致的姿态变化的人脸的形状和纹理表示。此外,我们的UT-AAM能够使用张量补全方法从不完整的训练数据集构建模型。最后,我们使用一个有效的级联回归为基础的方法UT-AAM拟合。随着这些进步,UT-AAM在实践中的实用性大大增强。作为一个例子,我们展示了通过使用UT-AAM合成大量虚拟样本来训练面部标志检测器的改进。在Multi-PIE和300-W人脸数据集上的实验结果验证了该方法的有效性。

英文摘要:

Appearance variations result in many difficulties in face image analysis. To deal with this challenge, we present a Unified Tensor-based Active Appearance Model (UT-AAM) for jointly modelling the geometry and texture information of 2D faces. For each type of face information, namely shape and texture, we construct a unified tensor model capturing all relevant appearance variations. This contrasts with the variation-specific models of the classical tensor AAM. To achieve the unification across pose variations, a strategy for dealing with self-occluded faces is proposed to obtain consistent shape and texture representations of pose-varied faces. In addition, our UT-AAM is capable of constructing the model from an incomplete training dataset, using tensor completion methods. Last, we use an effective cascaded-regression-based method for UT-AAM fitting. With these advancements, the utility of UT-AAM in practice is considerably enhanced. As an example, we demonstrate the improvements in training facial landmark detectors through the use of UT-AAM to synthesise a large number of virtual samples. Experimental results obtained using the Multi-PIE and 300-W face datasets demonstrate the merits of the proposed approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑