arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.18729cs.CV

Portrait4D:利用合成数据学习单样本4D头部虚拟人合成

Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data

Yu Deng, Duomin Wang, Xiaohang Ren, Xingyu Chen, Baoyuan Wang

AI总结:

针对3DMM限制单样本4D头部合成的问题,提出利用大规模合成数据,通过对抗学习生成多视角训练数据,并结合基于transformer的可动画三平面重建器与解耦学习策略,实现了优于现有技术的4D头部合成。

摘要:

现有的单样本4D头部合成方法通常借助3DMM重建从单目视频中学习,但3DMM重建同样具有挑战性,限制了合理的4D头部合成。我们提出一种通过大规模合成数据学习单样本4D头部合成的方法。关键在于首先通过对抗学习从单目图像中学习局部4D生成模型,以合成不同身份和完整动作的多视角图像作为训练数据;然后利用基于transformer的可动画三平面重建器,使用合成数据学习4D头部重建。通过解耦3D重建与重演的学习过程,采用一种新颖的学习策略来增强对真实图像的泛化能力。实验表明了我们的方法相对于先前技术的优越性。

英文摘要:

Existing one-shot 4D head synthesis methods usually learn from monocular videos with the aid of 3DMM reconstruction, yet the latter is evenly challenging which restricts them from reasonable 4D head synthesis. We present a method to learn one-shot 4D head synthesis via large-scale synthetic data. The key is to first learn a part-wise 4D generative model from monocular images via adversarial learning, to synthesize multi-view images of diverse identities and full motions as training data; then leverage a transformer-based animatable triplane reconstructor to learn 4D head reconstruction using the synthetic data. A novel learning strategy is enforced to enhance the generalizability to real images by disentangling the learning process of 3D reconstruction and reenactment. Experiments demonstrate our superiority over the prior art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑