Synthesizing dynamic appearances of humans in motion plays a central role in applications such as AR/VR and video editing. While many recent methods have been proposed to tackle this problem, handling loose garments with complex textures and high dynamic motion still remains challenging. In this paper, we propose a video based appearance synthesis method that tackles such challenges and demonstrates high quality results for in-the-wild videos that have not been shown before. Specifically, we adopt a StyleGAN based architecture to the task of person specific video based motion retargeting. We introduce a novel motion signature that is used to modulate the generator weights to capture dynamic appearance changes as well as regularizing the single frame based pose estimates to improve temporal coherency. We evaluate our method on a set of challenging videos and show that our approach achieves state-of-the art performance both qualitatively and quantitatively.
翻译:在AR/VR和视频编辑等应用软件中,动态人动态外观的合成工作发挥着核心作用。虽然提出了许多最近的方法来解决这一问题,但处理带有复杂质地和动态动态动态的松散服装仍具有挑战性。在本文中,我们提出了一种基于视频的外观合成方法,用以应对此类挑战,并展示以前从未展示过的全景视频的高质量结果。具体地说,我们采用了基于StyleGAN的StyleGAN结构来完成个人特定视频的运动重定向任务。我们引入了一种新的运动签名,用于调整生成器重量,以捕捉动态外观变化,并规范基于单一框架的估算,以提高时间一致性。我们用一套具有挑战性的视频来评估我们的方法,并表明我们的方法在质量和数量上都达到了艺术状态。