RigAnyFace: 基于未标注数据的神经面部网格自动 rigging 扩展
RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data
AI总结：
RigAnyFace通过基于未标注数据的2D监督策略，实现了对不同拓扑结构面部网格的高效自动rigging，支持多不连通组件，提升准确性和泛化能力。
摘要：
本文提出了RigAnyFace（RAF），一种可扩展的神经自动 rigging 框架，用于不同拓扑结构的面部网格，包括具有多个不连通组件的网格。RAF将静态中性面部网格变形为行业标准的FACS姿态，以形成具有表达性的混合形状rig。变形由一种三角化无关的表面学习网络预测，该网络通过我们的定制架构设计来条件于FACS参数，并高效处理不连通组件。在训练中，我们精心编纂了一个面部网格数据集，其中一部分由专业艺术家手工制作，用作准确的3D地面真实数据以监督变形。由于手动 rigging 的成本高，这部分数据集规模有限，限制了仅在此数据集上训练的模型的泛化能力。为了解决这个问题，我们设计了一种2D监督策略，用于未标注的中性网格，没有rig。这种策略增加了数据多样性，并允许扩展训练，从而增强了在增强数据上训练的模型的泛化能力。大量实验表明，RAF能够对不同拓扑结构的网格进行rigging，不仅在我们的艺术家制作的资产上，而且在野外样本中，优于先前的工作在准确性和泛化能力上。此外，我们的方法超越了先前的工作，支持多个不连通组件，如眼睛，以实现更详细的表达动画。项目页面：https://wenchao-m.github.io/RigAnyFace.github.io
英文摘要：
In this paper, we present RigAnyFace (RAF), a scalable neural auto-rigging framework for facial meshes of diverse topologies, including those with multiple disconnected components. RAF deforms a static neutral facial mesh into industry-standard FACS poses to form an expressive blendshape rig. Deformations are predicted by a triangulation-agnostic surface learning network augmented with our tailored architecture design to condition on FACS parameters and efficiently process disconnected components. For training, we curated a dataset of facial meshes, with a subset meticulously rigged by professional artists to serve as accurate 3D ground truth for deformation supervision. Due to the high cost of manual rigging, this subset is limited in size, constraining the generalization ability of models trained exclusively on it. To address this, we design a 2D supervision strategy for unlabeled neutral meshes without rigs. This strategy increases data diversity and allows for scaled training, thereby enhancing the generalization ability of models trained on this augmented data. Extensive experiments demonstrate that RAF is able to rig meshes of diverse topologies on not only our artist-crafted assets but also in-the-wild samples, outperforming previous works in accuracy and generalizability. Moreover, our method advances beyond prior work by supporting multiple disconnected components, such as eyeballs, for more detailed expression animation. Project page: https://wenchao-m.github.io/RigAnyFace.github.io
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。
