Geometry Driven Progressive Warping for One-Shot Face Animation
Yatao Zhong (Microsoft),* Faezeh Amjadi (Microsoft), Ilya Zharkov (Microsoft)
The 33rd British Machine Vision Conference
Abstract
Face animation aims at creating photo-realistic portrait videos with animated poses and expressions. A common practice is to generate displacement fields that are used to warp pixels and features from source to target. However, prior attempts often produce sub-optimal displacements. In this work, we present a geometry driven model and propose two geometric patterns as guidance: 3D face rendered displacement maps and posed neural codes. The model can optionally use one of the patterns as guidance for displacement estimation. To model displacements at locations not covered by the face model (e.g., hair), we resort to source image features for contextual information and propose a progressive warping module that alternates between feature warping and displacement estimation at increasing resolutions. We show that the proposed model can synthesize portrait videos with high fidelity and achieve the new state-of-the-art results on the VoxCeleb1 and VoxCeleb2 datasets for both cross identity and same identity reconstruction.Video
Citation
@inproceedings{Zhong_2022_BMVC,
author = {Yatao Zhong and Faezeh Amjadi and Ilya Zharkov},
title = {Geometry Driven Progressive Warping for One-Shot Face Animation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0357.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by