用自监督学习实现跨形状实时物理驱动的皮肤动画
PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
- 通过Transformer编码器与交叉注意力解码器构建神经皮肤场
- 支持不同网格划分，实现实时物理一致性变形
- 适合需要通用性与实时性的角色动画开发人员
实现跨多种3D形状和离散化方式的实时物理驱动动画仍是根本挑战。我们提出PhysSkin，一种物理感知框架。受线性混合皮肤（Linear Blend Skinning）启发，学习连续皮肤场作为基函数，将运动子空间坐标映射至全空间变形，子空间由控制点变换定义。为生成无需网格、与离散化无关且物理一致的皮肤场，并在多样3D形状间良好泛化，PhysSkin采用新型神经皮肤场自编码器，包含基于Transformer的编码器与交叉注意力解码器。此外，还设计了一种新颖的物理感知自监督学习策略，结合动态皮肤场归一化与冲突感知梯度修正，有效平衡能量最小化、空间平滑性与正交性约束。PhysSkin在通用神经皮肤建模上表现优异，支持实时物理驱动动画。
原文摘要 · Abstract (English)
Achieving real-time physics-based animation that generalizes across diverse 3D shapes and discretizations remains a fundamental challenge. We introduce PhysSkin, a physics-informed framework that addresses this challenge. In the spirit of Linear Blend Skinning, we learn continuous skinning fields as basis functions lifting motion subspace coordinates to full-space deformation, with subspace defined by handle transformations. To generate mesh-free, discretization-agnostic, and physically consistent skinning fields that generalize well across diverse 3D shapes, PhysSkin employs a new neural skinning fields autoencoder which consists of a transformer-based encoder and a cross-attention decoder. Furthermore, we also develop a novel physics-informed self-supervised learning strategy that incorporates on-the-fly skinning-field normalization and conflict-aware gradient correction, enabling effective balancing of energy minimization, spatial smoothness, and orthogonality constraints. PhysSkin shows outstanding performance on generalizable neural skinning and enables real-time physics-based animation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。