发表机构
Queen’s University; Vector Institute; Pickford AI; University of Toronto（女王大学; 向量研究所; 皮克福德人工智能公司; 多伦多大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TopoRig提出一种拓扑无关的面部绑定框架，通过多源监督在任意网格上直接预测FACS变形，保留拓扑并提升跨身份与拓扑的泛化能力。
AI 中文摘要
跨异构网格拓扑的自动面部绑定仍然具有挑战性，因为高质量的表达式监督通常与规范模板绑定，而将变形迁移到任意网格可能引入几何伪影和对应错误。我们提出了TopoRig，一种拓扑无关的面部绑定框架，直接在输入网格顶点上预测FACS条件下的变形，同时保留原始拓扑。从ICT FaceKit表情模型出发，我们构建了互补监督，包括准确但模板偏置的公共拓扑绑定、拓扑多样但噪声较大的迁移绑定，以及针对几何迁移难以捕获的控制点的基于图像的目标线索。TopoRig结合局部表面几何、地标相对语义特征、全局形状上下文和FACS控制来预测每个顶点的位移。我们使用来自53控制ICT FaceKit词汇表中的45个非凝视表情控制，在3,496个生成身份上训练。在保留身份和未见网格拓扑上，TopoRig比先前的神经面部绑定方法更忠实地再现参考表情空间，而定性结果显示在多样角色几何上的一致局部变形。消融研究表明，语义地标特征和互补监督改善了跨身份和跨拓扑的泛化。总体而言，TopoRig将异构和不完美的表情监督摊销为单个保持拓扑的变形模型。
英文摘要
Automatic facial rigging across heterogeneous mesh topologies remains challenging because high-quality expression supervision is often tied to canonical templates, while deformation transfer to arbitrary meshes can introduce geometric artifacts and correspondence errors. We present TopoRig, a topology-agnostic facial rigging framework that predicts FACS-conditioned deformations directly on input mesh vertices while preserving the original topology. Starting from the ICT FaceKit expression model, we construct complementary supervision from accurate but template-biased common-topology rigs, topology-diverse but noisier transferred rigs, and targeted image-based cues for controls poorly captured by geometric transfer. TopoRig combines local surface geometry, landmark-relative semantic features, global shape context, and FACS controls to predict per-vertex displacements. We train on 3,496 generated identities using 45 non-gaze expression controls from the 53-control ICT FaceKit vocabulary. On held-out identities and unseen mesh topologies, TopoRig more faithfully reproduces the reference expression space than prior neural facial-rigging methods, while qualitative results show consistent localized deformations across diverse character geometries. Ablations demonstrate that semantic landmark features and complementary supervision improve cross-identity and cross-topology generalization. Overall, TopoRig amortizes heterogeneous and imperfect expression supervision into a single topology-preserving deformation model.
Comments15 pages, 6 figures. Project page: https://andrewjmfleet.github.io/TopoRig/
