PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF

TL;DR

PIE-NeRF integrates physics-based elastodynamics with NeRF using a meshless discretization approach, enabling realistic, interactive animations of complex hyperelastic objects without auxiliary shape proxies.

Contribution

It introduces a meshless nonlinear hyperelasticity discretization integrated with NeRF, allowing versatile and efficient elastodynamics simulations of complex shapes.

Findings

Realistic elastodynamics animations at interactive rates.

Meshless discretization simplifies complex shape simulations.

Adaptive kernel placement reduces computational complexity.

Abstract

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/.