首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition >Mesoscopic Facial Geometry Inference Using Deep Neural Networks
【24h】

Mesoscopic Facial Geometry Inference Using Deep Neural Networks

机译:使用深层神经网络的介观面部几何推理

获取原文

摘要

We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps. When applied to an image sequence, the synthesized detail is temporally coherent. Unlike current state-of-the-art methods [17, 5], which assume 'dark is deep', our model is trained with measured facial detail collected using polarized gradient illumination in a Light Stage [20]. This enables us to produce plausible facial detail across the entire face, including where previous approaches may incorrectly interpret dark features as concavities such as at moles, hair stubble, and occluded pores. Instead of directly inferring 3D geometry, we propose to encode fine details in high-resolution displacement maps which are learned through a hybrid network adopting the state-of-the-art image-to-image translation network [29] and super resolution network [43]. To effectively capture geometric detail at both mid- and high frequencies, we factorize the learning into two separate sub-networks, enabling the full range of facial detail to be modeled. Results from our learning-based approach compare favorably with a high-quality active facial scanhening technique, and require only a single passive lighting condition without a complex scanning setup.
机译:我们提出了一种基于学习的方法,用于从弥散照明的面部纹理贴图合成中等和精细比例的面部几何。当应用于图像序列时,合成细节在时间上是连贯的。与当前假设“黑暗很深”的最新技术[17,5]不同,我们的模型是通过在Light Stage [20]中使用偏振梯度照明收集的面部细节来训练的。这使我们能够在整个面部上产生合理的面部细节,包括以前的方法可能错误地将深色特征解释为凹陷的现象,例如痣,发茬和阻塞的毛孔。与其直接推断3D几何形状,我们建议在高分辨率位移图中编码精细细节,这些细节是通过采用最新图像到图像转换网络[29]和超分辨率网络[ 43]。为了有效地捕获中高频处的几何细节,我们将学习分解为两个独立的子网络,从而可以对整个面部细节进行建模。我们基于学习的方法的结果可与高质量的主动面部扫描技术相媲美,并且只需要一个被动照明条件,而无需复杂的扫描设置。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号