Synthesizing dynamic appearances of humans in motion plays a central role in\napplications such as AR/VR and video editing. While many recent methods have\nbeen proposed to tackle this problem, handling loose garments with complex\ntextures and high dynamic motion still remains challenging. In this paper, we\npropose a video based appearance synthesis method that tackles such challenges\nand demonstrates high quality results for in-the-wild videos that have not been\nshown before. Specifically, we adopt a StyleGAN based architecture to the task\nof person specific video based motion retargeting. We introduce a novel motion\nsignature that is used to modulate the generator weights to capture dynamic\nappearance changes as well as regularizing the single frame based pose\nestimates to improve temporal coherency. We evaluate our method on a set of\nchallenging videos and show that our approach achieves state-of-the art\nperformance both qualitatively and quantitatively.\n