发表机构
KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出PDB方法，通过预测控制点和混合权重实现无网格依赖的面部动画重定向，仅用自监督训练支持跨身份迁移，减少表面伪影并保持表情质量。
AI 中文摘要
与网格无关的面部动画重定向能够跨不同结构的网格传递表情，但在无表面伪影的情况下保持面部运动仍然具有挑战性。为解决这一问题，我们提出了PDB，即基于点的形变混合（Point-Based Deformation Blending），用于面部动画重定向。PDB从源中性表情对中预测一组紧凑的形变控制点，并从目标中性网格中预测混合权重。权重对每个目标仅计算一次并在帧间复用，而控制点则随每个源表情变化。ReLU激活函数强制权重非负并允许精确的零值，随后进行逐行归一化。目标网格通过直接乘以权重和控制点来重建，无需预定义的笼子（cage）、预计算的坐标、学习的逐元素形变解码器或全局重建求解。仅使用自重定向重建监督进行训练，PDB支持跨身份迁移，而无需配对的跨身份训练表情。实验证明了准确的重新定向、快速推理以及学习权重中的局部支持。表情准确性和局部表面保持的联合评估显示，与所评估的密集位移方法相比，表面伪影减少，同时保留了预期的运动。感知评估进一步支持了自重定向和跨重定向中的表情保真度和视觉质量。
英文摘要
Mesh-agnostic facial animation retargeting transfers expressions across meshes with different structures, but preserving facial motion without surface artifacts remains challenging. To address this, we present PDB, Point-Based Deformation Blending for facial animation retargeting. PDB predicts a compact set of deformed control points from a source neutral-expression pair and blending weights from the target neutral mesh. The weights are computed once per target and reused across frames, while the control points vary with each source expression. ReLU enforces non-negative weights and permits exact zeros, followed by row-wise normalization. The target mesh is reconstructed directly by multiplying the weights and control points, without a predefined cage, precomputed coordinates, a learned per-element deformation decoder, or a global reconstruction solve. Trained only with self-retargeting reconstruction supervision, PDB supports cross-identity transfer without paired cross-identity training expressions. Experiments demonstrate accurate retargeting, fast inference, and localized support in the learned weights. Joint evaluation of expression accuracy and local surface preservation shows reduced surface artifacts relative to the evaluated dense displacement method while retaining the intended motion. Perceptual evaluations further support expression fidelity and visual quality in both self- and cross-retargeting.
