Saved in:
Bibliographic Details
Main Authors: Ostrek, Mirela, Thies, Justus
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.18083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914958079426560
author Ostrek, Mirela
Thies, Justus
author_facet Ostrek, Mirela
Thies, Justus
contents Rapid advances in the field of generative AI and text-to-image methods in particular have transformed the way we interact with and perceive computer-generated imagery today. In parallel, much progress has been made in 3D face reconstruction, using 3D Morphable Models (3DMM). In this paper, we present SVP, a novel hybrid 2D/3D generation method that outputs photorealistic videos of talking faces leveraging a large pre-trained text-to-image prior (2D), controlled via a 3DMM (3D). Specifically, we introduce a person-specific fine-tuning of a general 2D stable diffusion model which we lift to a video model by providing temporal 3DMM sequences as conditioning and by introducing a temporal denoising procedure. As an output, this model generates temporally smooth imagery of a person with 3DMM-based controls, i.e., a person-specific avatar. The facial appearance of this person-specific avatar can be edited and morphed to text-defined celebrities, without any fine-tuning at test time. The method is analyzed quantitatively and qualitatively, and we show that our method outperforms state-of-the-art monocular head avatar methods.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18083
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stable Video Portraits
Ostrek, Mirela
Thies, Justus
Computer Vision and Pattern Recognition
Rapid advances in the field of generative AI and text-to-image methods in particular have transformed the way we interact with and perceive computer-generated imagery today. In parallel, much progress has been made in 3D face reconstruction, using 3D Morphable Models (3DMM). In this paper, we present SVP, a novel hybrid 2D/3D generation method that outputs photorealistic videos of talking faces leveraging a large pre-trained text-to-image prior (2D), controlled via a 3DMM (3D). Specifically, we introduce a person-specific fine-tuning of a general 2D stable diffusion model which we lift to a video model by providing temporal 3DMM sequences as conditioning and by introducing a temporal denoising procedure. As an output, this model generates temporally smooth imagery of a person with 3DMM-based controls, i.e., a person-specific avatar. The facial appearance of this person-specific avatar can be edited and morphed to text-defined celebrities, without any fine-tuning at test time. The method is analyzed quantitatively and qualitatively, and we show that our method outperforms state-of-the-art monocular head avatar methods.
title Stable Video Portraits
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.18083