SIGGRAPH Asia 2022 VToonify: Controllable High Resolution Portrait Video Style Transfer

Code: Project: Paper: Web demo: Abstract: Generating highquality artistic portrait videos is an important and desirable task in computer graphics and vision. Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these imageoriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing nonfacial details and temporal inconsistency. In this work, we investigate the challenging controllable highresolution portrait video style transfer by introducing a novel VToonify framework. Specifically, VToonify leverages the mid and highresolution layers of StyleGAN to render highquality artistic portraits based on the multiscale content features extracted by an encoder to better preserve the br, br,