Expressive Talking Head Video Encoding in StyleGAN2 Latent Space

Trevine Oorloff, Yaser Yacoob; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 2998-3007

While the recent advances in research on video re-enactment have yielded promising results, the existing approaches fall short in capturing the fine, detailed, and expressive facial features (e.g., lip-pressing, mouth puckering, mouth gaping, and wrinkles), which are crucial in generating realistic animated face videos. To this end, we propose an end-to-end expressive face video encoding approach that facilitates data-efficient high-quality video re-synthesis by optimizing low-dimensional edits of a single Identity-latent. The approach builds on StyleGAN2 image inversion and multi-stage non-linear latent space editing to generate videos that are nearly comparable to input videos. While existing StyleGAN latent-based editing techniques focus on simply generating plausible edits of static images, we automate the latent space editing to capture the fine expressive facial deformations in a sequence of frames using an encoding that resides in the Style-latent space (StyleSpace) of StyleGAN2. The encoding thus obtained could be super-imposed on a single Identity-latent to facilitate re-enactment of high-resolution face videos at 1024^2. The proposed framework economically captures face identity, head-pose, and complex expressive facial motions at fine levels, and thereby bypasses training, person modeling, dependence on landmarks/keypoints, and low-resolution synthesis which tend to hamper most re-enactment approaches. The proposed method is designed with maximum data efficiency, where a single W+ latent and 35 parameters per frame enable high-fidelity video rendering. This pipeline can also be used for puppeteering (i.e., motion transfer). Project page: https://trevineoorloff.github.io/ExpressiveFaceVideoEncoding.io/.