arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.02935cs.CV
收藏

基于域工程的参数化人脸单目重建

Applied monocular reconstruction of parametric faces with domain engineering

Electronic Arts(美国艺电)

Igor Borovikov, Karine Levonyan, Jon Rein, Pawel Wrotek, Nitish Victor

摘要:

许多现代在线3D应用程序和视频游戏依赖于人脸的参数化模型来创建可信的化身。然而,用参数化模型手动再现某人的面部相似性是困难且耗时的。针对该任务的机器学习解决方案是非常可取的,但也具有挑战性。提出了一种新的人脸参数化问题(F2 P)的解决方法,旨在从一幅图像中重建出参数化的人脸。所提出的方法利用合成数据,区域分解,和领域自适应解决多方面的挑战,在解决F2 P。开源代码库说明了我们的主要观察结果,并提供了定量评估的方法。所提出的方法在工业应用中证明是实用的;它提高了准确性,并允许更有效的模型训练。该技术有可能扩展到其他类型的参数模型。

英文摘要:

Many modern online 3D applications and videogames rely on parametric models of human faces for creating believable avatars. However, manual reproduction of someone's facial likeness with a parametric model is difficult and time-consuming. Machine Learning solution for that task is highly desirable but is also challenging. The paper proposes a novel approach to the so-called Face-to-Parameters problem (F2P for short), aiming to reconstruct a parametric face from a single image. The proposed method utilizes synthetic data, domain decomposition, and domain adaptation for addressing multifaceted challenges in solving the F2P. The open-sourced codebase illustrates our key observations and provides means for quantitative evaluation. The presented approach proves practical in an industrial application; it improves accuracy and allows for more efficient models training. The techniques have the potential to extend to other types of parametric models.

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。

↑