Dense 3D Face Alignment from 2D Videos in Real-Time.
Dense 3D Face Alignment from 2D Videos in Real-Time.
复制标题
DOI：
10.1109/fg.2015.7163142
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
Kanade T
中科院分区：
文献类型：
--
作者：
Jeni LA;Cohn JF;Kanade T
为了能够从2D视频中实时地进行独立于人的3D配准，我们开发了一种3D级联回归方法，在该方法中，面部地标在大约60度的范围内保持不变。从人的面部的单个2D图像，为每一帧实时记录密集的3D形状。该算法利用一种快速的级联回归框架，对姿态和自发表情的高分辨率3D人脸扫描进行训练。该算法首先估计密集标记集的位置及其可见性，然后通过拟合基于零件的3D模型来重建人脸形状。由于不需要关于照明或表面属性的假设，该方法可以应用于广泛的成像条件，包括2D视频和未校准的多视点视频。该方法已经在一系列实验中得到了验证，这些实验评估了该方法的三维重建精度并将其扩展到多视角重建。实验结果有力地支持了从2D视频进行实时、3D配准和重建的有效性。该软件可在http://zface.org.上在线购买
To enable real-time, person-independent 3D registration from 2D video, we developed a 3D cascade regression approach in which facial landmarks remain invariant across pose over a range of approximately 60 degrees. From a single 2D image of a person's face, a dense 3D shape is registered in real time for each frame. The algorithm utilizes a fast cascade regression framework trained on high-resolution 3D face-scans of posed and spontaneous emotion expression. The algorithm first estimates the location of a dense set of markers and their visibility, then reconstructs face shapes by fitting a part-based 3D model. Because no assumptions are required about illumination or surface properties, the method can be applied to a wide range of imaging conditions that include 2D video and uncalibrated multi-view video. The method has been validated in a battery of experiments that evaluate its precision of 3D reconstruction and extension to multi-view reconstruction. Experimental findings strongly support the validity of real-time, 3D registration and reconstruction from 2D video. The software is available online at http://zface.org.