arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03029cs.CVcs.GR
收藏

HHAvatar:具有动态头发的高斯头部化身

HHAvatar: Gaussian Head Avatar with Dynamic Hairs

Tsinghua University(清华大学);Huawei Technologies Co Ltd(华为技术有限公司);Beijing Normal University(北京师范大学)

Zhanfeng Liao, Yuelang Xu, Zhe Li, Qijing Li, Boyao Zhou, Ruifeng Bai, Di Xu, Hongwen Zhang, Yebin Liu

AI总结:

HHAvatar提出用可控三维高斯联合MLP形变场建模高保真头部化身,并通过几何引导初始化、混合头部模型与遮挡感知模块解决稀疏视图下动态头发建模难题,在2K分辨率下实现领先的渲染质量。

摘要:

创建高保真三维头部化身一直是研究热点,但在轻量级稀疏视图设置下仍然面临巨大挑战。本文提出了一种由可控三维高斯表示的HHAvatar,用于具有动态头发建模的高保真头部化身。我们首先使用三维高斯来表示头部的外观,然后联合优化中性三维高斯和一个完全学习的基于MLP的形变场来捕捉复杂表情。这两部分相互促进,因此我们的方法能够在确保表情准确性的同时建模细粒度动态细节。此外,我们设计了一种基于隐式SDF和Deep Marching Tetrahedra的精心设计的几何引导初始化策略,以保证训练过程的稳定性和收敛性。为了解决动态头发建模问题,我们在基于高斯头部化身的化身表示中引入了混合头部模型,并提出了一种考虑时序信息的训练方法和一个遮挡感知模块来建模头发的非刚性运动。实验表明,我们的方法优于其他最先进的稀疏视图方法,即使在夸张表情下也能在2K分辨率下实现超高保真渲染质量,并能合理地驱动头发随头部运动。

英文摘要:

Creating high-fidelity 3D head avatars has always been a research hotspot, but it remains a great challenge under lightweight sparse view setups. In this paper, we propose HHAvatar represented by controllable 3D Gaussians for high-fidelity head avatar with dynamic hair modeling. We first use 3D Gaussians to represent the appearance of the head, and then jointly optimize neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. To address the problem of dynamic hair modeling, we introduce a hybrid head model into our avatar representation based Gaussian Head Avatar and a training method that considers timing information and an occlusion perception module to model the non-rigid motion of hair. Experiments show that our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions and driving hairs reasonably with the motion of the head

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。

↑