PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Yutao, Shang, Yintong, Li, Xuan, Shao, Tianjia, Jiang, Chenfanfu, Yang, Yin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911817523003392
author Feng, Yutao
Shang, Yintong
Li, Xuan
Shao, Tianjia
Jiang, Chenfanfu
Yang, Yin
author_facet Feng, Yutao
Shang, Yintong
Li, Xuan
Shao, Tianjia
Jiang, Chenfanfu
Yang, Yin
contents We show that physics-based simulations can be seamlessly integrated with NeRF to generate high-quality elastodynamics of real-world objects. Unlike existing methods, we discretize nonlinear hyperelasticity in a meshless way, obviating the necessity for intermediate auxiliary shape proxies like a tetrahedral mesh or voxel grid. A quadratic generalized moving least square (Q-GMLS) is employed to capture nonlinear dynamics and large deformation on the implicit model. Such meshless integration enables versatile simulations of complex and codimensional shapes. We adaptively place the least-square kernels according to the NeRF density field to significantly reduce the complexity of the nonlinear simulation. As a result, physically realistic animations can be conveniently synthesized using our method for a wide range of hyperelastic materials at an interactive rate. For more information, please visit our project page at https://fytalon.github.io/pienerf/.
format Preprint
id arxiv_https___arxiv_org_abs_2311_13099
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF
Feng, Yutao
Shang, Yintong
Li, Xuan
Shao, Tianjia
Jiang, Chenfanfu
Yang, Yin
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
We show that physics-based simulations can be seamlessly integrated with NeRF to generate high-quality elastodynamics of real-world objects. Unlike existing methods, we discretize nonlinear hyperelasticity in a meshless way, obviating the necessity for intermediate auxiliary shape proxies like a tetrahedral mesh or voxel grid. A quadratic generalized moving least square (Q-GMLS) is employed to capture nonlinear dynamics and large deformation on the implicit model. Such meshless integration enables versatile simulations of complex and codimensional shapes. We adaptively place the least-square kernels according to the NeRF density field to significantly reduce the complexity of the nonlinear simulation. As a result, physically realistic animations can be conveniently synthesized using our method for a wide range of hyperelastic materials at an interactive rate. For more information, please visit our project page at https://fytalon.github.io/pienerf/.
title PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
url https://arxiv.org/abs/2311.13099