PhysSkin：基于自监督神经蒙皮的实时可泛化物理动画
PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
把线性混合蒙皮推广为连续神经蒙皮场，用 Transformer 编码器加交叉注意力解码器从手柄变换生成与离散化无关的形变基函数，可直接用于实时角色动画与物理仿真中的任意网格或点云驱动。
原文依据 PhysSkin employs a new neural skinning fields autoencoder which consists of a transformer-based encoder and a cross-attention decoder.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论实现可跨多样三维形状与离散化方式泛化的实时物理动画仍是一项基础性挑战。本文提出 PhysSkin，一个物理信息驱动的框架来应对该挑战。遵循线性混合蒙皮的思想，我们将连续蒙皮场学习为基函数，把运动子空间坐标提升为全空间形变，其中子空间由手柄变换定义。为生成无网格、与离散化无关且物理一致的蒙皮场，并使其在多样三维形状上良好泛化，PhysSkin 采用一种新的神经蒙皮场自编码器，由基于 Transformer 的编码器与交叉注意力解码器组成。此外，我们还提出一种新的物理信息自监督学习策略，融合即时蒙皮场归一化与冲突感知梯度校正，从而有效平衡能量最小化、空间平滑性与正交性约束。PhysSkin 在可泛化神经蒙皮上表现优异，并支持实时物理动画。
英文原文摘要 1107 字符
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.