GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed Materials

TL;DR

GaussianFluent addresses the limitations of 3D Gaussian Splatting by enabling coherent interior textures and physically grounded brittle fracture for mixed-material objects. It introduces a training-free internal texture synthesis pipeline and an optimized GPU-accelerated CD-MPM that supports mixed materials and continuous return mapping, enabling real-time, photorealistic dynamic scenes. The approach yields high-fidelity interior structures and plausible topological changes under challenging scenarios such as bullet impacts, slicing, and fluid-like behavior, outperforming prior GS methods in both visuals and dynamics. This framework broadens the applicability of Gaussian Splatting to interactive VR, robotics, and other domains requiring realistic, dynamic 3D scenes with mixed materials and fracture phenomena.

Abstract

3D Gaussian Splatting (3DGS) has emerged as a prominent 3D representation for high-fidelity and real-time rendering. 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: the lack of volumetric interiors with coherent textures in GS representation, and 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 GaussianFluent's capability for photo-realistic, real-time rendering with structurally consistent interiors, highlighting its potential for downstream application, such as VR and Robotics.

Figures (10)

• Figure 1: Physical simulation of dynamic object states with 3dgs.GaussianFluent is capable of generating realistic internal texture, simulating and rendering complex object dynamics (e.g., elastic deformation, fracture, and slicing) with mixed materials (e.g., jelly with internal blue sugar penetrated by a rigid bullet in top row), in response to different lighting conditions.
• Figure 2: Internal Gaussian filling and refinement. The opacity optimization improves the smoothness of the gs surface after internal filling, beneficial for texture inpainting and simulation.
• Figure 3: Overview of GaussianFluent. Our model first populates Gaussians in the internal volume and generates interior realistic texture with pretrained image generative models (\ref{['sec:gs_inpaint']}). We then incorporate optimized CD-MPM simulation with mixed materials for Gaussian Splatting (\ref{['sec:cdmpm']}) and introduce Blinn-Phong reflection in the rendering pipeline ( Supplementary\ref{['sec:phong']}).
• Figure 4: A jelly-like material is shot with a bullet. We compare our method with PhysGaussian to demonstrate the effectiveness of our simulation and visualize the damage variable $\alpha$.
• Figure 5: Comparison between our mixed material modeling and fixed $\beta$ setting. Our approach assigns distinct $\beta$ values, i.e., 2, 0.6, and 5, to the rind, flesh, and seed, respectively. This yields more realistic simulation results compared to settings that apply a single, uniform $\beta$ value to the entire watermelon.