Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis
This addresses the problem of realistic human animation for AR/VR and video editing applications, but it is incremental as it builds on existing StyleGAN-based methods with novel motion signatures.
The paper tackles the challenge of synthesizing dynamic appearances for humans in motion, particularly for loose garments with complex textures and high dynamic motion in in-the-wild videos, achieving state-of-the-art performance both qualitatively and quantitatively.
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.