Neuroll：基于模拟器在环展开的实时神经发丝模拟
Neuroll: Real-Time Neural Strand-Based Hair Simulation via Simulator-in-the-Loop Unrolling
- Meta
- Meta Reality Labs
- NVIDIA（英伟达）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对实时发丝模拟，提出模拟器在环展开的神经时间积分器，自监督训练，实现跨发型、材质、身体运动等泛化，稳定长视野且支持准静态模拟。
AI中文摘要：
时间积分一直是基于物理的动画的基石，它使得刚体和可变形物体之间的复杂交互（包括头发的运动）得以模拟。尽管最近在优化时间积分方面取得了进展，使得数千根发丝能够实时模拟，但在商用硬件上实现相同性能仍然不可行，因为解决数千根独立发丝之间的复杂动力学和交互需要巨大的计算量。随着基于学习的技术兴起，将时间积分卸载到神经网络有助于实现显著的性能提升，使这些方法适用于游戏和虚拟化身等实时应用。然而，最先进的神经技术往往产生物理上不太合理的运动，并且常常无法泛化到分布外场景。受经典时间积分器的启发，我们设计了一个神经对应物，它镜像了其输入输出公式——将先前的头发状态、材料刚度和碰撞几何作为神经时间积分器的输入，然后通过自监督的、模拟器在环的方法进行训练，并采用随机展开视野。通过在每个发丝的局部坐标系中制定训练，我们获得了一个在多个维度上泛化的网络，包括发型、材料属性、身体运动和身体类型。我们的方法继承了基于发丝的神经模拟器的优点，因此具有密度无关、轻量级、内存高效和高性能的特点。我们的神经头发积分器产生稳定的长视野展开，并且可以通过简单地重置头发状态自然地扩展到支持准静态模拟。
英文摘要：
Time integration has been the cornerstone of physics-based animation that enables the simulation of complex interactions between rigid and deformable objects, including the motion of hair. Despite recent advances with optimized time integration that enabled thousands of hair strands to be simulated in real time, achieving the same performance on commodity hardware remains infeasible due to the computational demands of resolving complex dynamics and interactions between thousands of individual strands. With the rise of learning-based techniques, the offload of time integration to neural networks helps to achieve significant performance gains, making these approaches suitable for real-time applications such as gaming and virtual avatars. However, state-of-the-art neural techniques tend to produce less physically plausible motion and oftentimes fail to generalize to out-of-distribution scenarios. Inspired by classical time integrators, we design a neural counterpart that mirrors their input-output formulation -- taking previous hair states, material stiffness, and collision geometry as the inputs for the neural time integrator, which is then trained via a self-supervised, simulator-in-the-loop method with randomized unrolling horizons. By formulating training in each strand's local coordinate frame, we obtain a network that generalizes across multiple dimensions, including hairstyle, material property, body motion, and body type. Our method inherits the benefits of a strand-based neural simulator, and hence is density-independent, lightweight, memory-efficient, and performant. Our neural hair integrator produces stable long-horizon rollouts and can be naturally extended to support quasi-static simulation simply by resetting hair states.
