Yuan Gong, Yong Zhang*, Xiaodong Cun, Yin Fei, Yanbo Fan, Xuan Wang,
Baoyuan Wu, Yujiu Yang*
(* Corresponding Authors)
teaser.mp4
We target cross-domain face reenactment in this paper, i.e., driving a cartoon image with the video of a real person and vice versa. Recently, many works have focused on one-shot talking face generation to drive a portrait with a real video, i.e., within-domain reenactment. Straightforwardly applying those methods to cross-domain animation will cause inaccurate expression transfer, blur effects, and even apparent artifacts due to the domain shift between cartoon and real faces. Only a few works attempt to settle cross-domain face reenactment. The most related work AnimeCeleb requires constructing a dataset with pose vector and cartoon image pairs by animating 3D characters, which makes it inapplicable anymore if no paired data is available. In this paper, we propose a novel method for cross-domain reenactment without paired data. Specifically, we propose a transformer-based framework to align the motions from different domains into a common latent space where motion transfer is conducted via latent code addition. Two domain-specific motion encoders and two learnable motion base memories are used to capture domain properties. A source query transformer and a driving one are exploited to project domain-specific motion to the canonical space. The edited motion is projected back to the domain of the source with a transformer. Moreover, since no paired data is provided, we propose a novel cross-domain training scheme using data from two domains with the designed analogy constraint. Besides, we contribute a cartoon dataset in Disney style. Extensive evaluations demonstrate the superiority of our method over competing methods.
R2C1.mp4
R2C2.mp4
C2R_1.mp4
C2R_2.mp4
indomain1.mp4
indomain2.mp4
@misc{gong2023toontalker,
title={ToonTalker: Cross-Domain Face Reenactment},
author={Gong Yuan and Zhang Yong and Cun Xiaodong and Yin Fei and Fan Yanbo and Wang Xuan and Wu Baoyuan and Yang Yujiu},
year={2023},
eprint={2308.12866},
archivePrefix={arXiv},
primaryClass={cs.CV}
}