MrNeRF (@janusch_patas)

2026-01-15 | โค๏ธ 96 | ๐Ÿ” 13


GaussianFluent: Explicit Gaussian Simulation for Dynamic Object States with Mixed Materials

Abstract (excerpt): Prior work has coupled physics simulation with Gaussians but predominantly targets soft, deformable materials, leaving brittle fracture largely unresolved. This stems from two key obstacles:

  1. The lack of volumetric interiors with coherent textures in GS representation.
  2. The absence of fracture-aware simulation methods for Gaussians.

To address these challenges, we introduce GaussianFluent, a unified framework for realistic simulation and rendering of dynamic object states.

First, it synthesizes photorealistic interiors by densifying internal Gaussians guided by generative models. Second, it integrates an optimized Continuum Damage Material Point Method (CD-MPM) to enable brittle fracture simulation at remarkably high speed.

Our approach handles complex scenarios, including mixed-material objects and multi-stage fracture propagation, achieving results infeasible with previous methods. Experiments clearly demonstrate GaussianFluentโ€™s capability for photo-realistic, real-time rendering with structurally consistent interiors, highlighting its potential for downstream applications such as VR and Robotics.

๋ฏธ๋””์–ด

image


Auto-generated - needs manual review

Tags

3D Rendering Robotics AI-ML GenAI Simulation