{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/encode-in-style-latent-based-video-encoding","title":"Expressive Talking Head Video Encoding in StyleGAN2 Latent-Space","arxiv_id":"2203.14512","date":"2022-03-28","proceeding":null,"authors":["Trevine Oorloff","Yaser Yacoob"],"abstract":"While the recent advances in research on video reenactment have yielded promising results, the 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 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 approach 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).","url_abs":"https://arxiv.org/abs/2203.14512v2","url_pdf":"https://arxiv.org/pdf/2203.14512v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"encode-in-style-latent-based-video-encoding","repo_url":"https://github.com/trevineoorloff/Encode-in-Style","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"encode-in-style-latent-based-video-encoding","repo_url":"https://github.com/DavieHR/expressive_talkinghead_encoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"adaptive-instance-normalization","method_name":"Adaptive Instance Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"path-length-regularization","method_name":"Path Length Regularization"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"},{"method_slug":"stylegan","method_name":"StyleGAN"},{"method_slug":"weight-demodulation","method_name":"Weight Demodulation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.14512","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}