人工智能(AI)分析报告-NVIDIA：使用深层神经网络的面部性能捕获.Facial Performance Capture with Deep Neural Networks.docxVIP

Facial Performance Capture with Deep Neural NetworksAbstractWe present a deep learning technique for facial performance cap- ture, i.e., the transfer of video footage into a motion sequence of a 3D mesh representing an actor’s face. Specifically, we build on aConventional capture pipelineTarget vertex positionsconventional capture pipeline based on computer vision and multi- view video, and use its results to train a deep neural network to produce similar output from a monocular video sequence. Once trained, our network produces high-quality results for unseen inputsTraining footageNeural net