arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08364cs.CVcs.LG
收藏

一种用于计算机视觉的高保真合成人脸框架

A high fidelity synthetic face framework for computer vision

Microsoft(微软)

Tadas Baltrusaitis, Erroll Wood, Virginia Estellers, Charlie Hewitt, Sebastian Dziadzio, Marek Kowalski, Matthew Johnson, Thomas J. Cashman, Jamie Shotton

摘要:

人脸分析是计算机视觉的核心应用之一,其任务范围包括地标对齐、头部姿态估计、表情识别和人脸识别等。然而,构建可靠的方法需要耗时的数据汇集,并且通常需要更耗时的手动注释,这可能是不可靠的。在我们的工作中,我们提出合成这样的面部数据,包括地面实况注释,这几乎是不可能通过手动注释获得的一致性和规模可能通过使用合成数据。我们使用参数化的人脸模型和手工制作的资产,使我们能够生成具有前所未有的质量和多样性(不同的形状,纹理,表情,姿势,灯光和头发)的训练数据。

英文摘要:

Analysis of faces is one of the core applications of computer vision, with tasks ranging from landmark alignment, head pose estimation, expression recognition, and face recognition among others. However, building reliable methods requires time-consuming data collection and often even more time-consuming manual annotation, which can be unreliable. In our work we propose synthesizing such facial data, including ground truth annotations that would be almost impossible to acquire through manual annotation at the consistency and scale possible through use of synthetic data. We use a parametric face model together with hand crafted assets which enable us to generate training data with unprecedented quality and diversity (varying shape, texture, expression, pose, lighting, and hair).

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。

↑