Quaffure: Real-Time Quasi-Static Neural Hair Simulation

TL;DR

Quaffure introduces a neural method for real-time, physically plausible hair deformation prediction that generalizes across diverse poses and hairstyles, enabling smooth, scalable avatar animations on consumer hardware.

Contribution

It presents a self-supervised neural model for real-time hair simulation that generalizes well and is computationally efficient for practical applications.

Findings

Achieves inference in a few milliseconds on consumer hardware.

Successfully scales to predict the drape of 1000 grooms in 0.3 seconds.

Demonstrates robust generalization across poses, shapes, and hairstyles.

Abstract

Realistic hair motion is crucial for high-quality avatars, but it is often limited by the computational resources available for real-time applications. To address this challenge, we propose a novel neural approach to predict physically plausible hair deformations that generalizes to various body poses, shapes, and hairstyles. Our model is trained using a self-supervised loss, eliminating the need for expensive data generation and storage. We demonstrate our method's effectiveness through numerous results across a wide range of pose and shape variations, showcasing its robust generalization capabilities and temporally smooth results. Our approach is highly suitable for real-time applications with an inference time of only a few milliseconds on consumer hardware and its ability to scale to predicting the drape of 1000 grooms in 0.3 seconds. Please see our project page here following https://tuurstuyck.github.io/quaffure/quaffure.html