Quaffure: Real-Time Quasi-Static Neural Hair Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Stuyck, Tuur, Lin, Gene Wei-Chin, Larionov, Egor, Chen, Hsiao-yu, Bozic, Aljaz, Sarafianos, Nikolaos, Roble, Doug
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915237471453184
author Stuyck, Tuur
Lin, Gene Wei-Chin
Larionov, Egor
Chen, Hsiao-yu
Bozic, Aljaz
Sarafianos, Nikolaos
Roble, Doug
author_facet Stuyck, Tuur
Lin, Gene Wei-Chin
Larionov, Egor
Chen, Hsiao-yu
Bozic, Aljaz
Sarafianos, Nikolaos
Roble, Doug
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2412_10061
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quaffure: Real-Time Quasi-Static Neural Hair Simulation
Stuyck, Tuur
Lin, Gene Wei-Chin
Larionov, Egor
Chen, Hsiao-yu
Bozic, Aljaz
Sarafianos, Nikolaos
Roble, Doug
Computer Vision and Pattern Recognition
Graphics
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
title Quaffure: Real-Time Quasi-Static Neural Hair Simulation
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.10061