FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction

• URL: http://arxiv.org/abs/2603.21356v2
• Date: Fri, 27 Mar 2026 20:26:21 GMT
• Title: FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction
• Abstract summary: We propose a plug-and-play method that tightly couples geometry reconstruction with ubiquitous fluid-structure interactions to assess surface quality at high granularity.<n>Our FluidGaussian method yields up to +8.6% visual PSNR (Peak Signal-to-Noise Ratio) and -62.3% velocity divergence during fluid simulations.
• Score: 37.29218600173778
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real objects that inhabit the physical world follow physical laws and thus behave plausibly during interaction with other physical objects. However, current methods that perform 3D reconstructions of real-world scenes from multi-view 2D images optimize primarily for visual fidelity, i.e., they train with photometric losses and reason about uncertainty in the image or representation space. This appearance-centric view overlooks body contacts and couplings, conflates function-critical regions (e.g., aerodynamic or hydrodynamic surfaces) with ornamentation, and reconstructs structures suboptimally, even when physical regularizers are added. All these can lead to unphysical and implausible interactions. To address this, we consider the question: How can 3D reconstruction become aware of real-world interactions and underlying object functionality, beyond visual cues? To answer this question, we propose FluidGaussian, a plug-and-play method that tightly couples geometry reconstruction with ubiquitous fluid-structure interactions to assess surface quality at high granularity. We define a simulation-based uncertainty metric induced by fluid simulations and integrate it with active learning to prioritize views that improve both visual and physical fidelity. In an empirical evaluation on NeRF Synthetic (Blender), Mip-NeRF 360, and DrivAerNet++, our FluidGaussian method yields up to +8.6% visual PSNR (Peak Signal-to-Noise Ratio) and -62.3% velocity divergence during fluid simulations. Our code is available at https://github.com/delta-lab-ai/FluidGaussian.

Related papers

• PhysiFormer: Learning to Simulate Mechanics in World Space [56.16644631495]
  We present PhysiFormer, a diffusion transformer for physically-plausible 3D object motion.<n>It represents objects as 3D meshes expressed in world coordinates.<n>It substantially outperforms autoregressive baselines in trajectory accuracy, rigidity preservation, and momentum-based physical consistency.
  arXiv  Detail & Related papers  (2026-06-25T17:59:00Z)
• Real-to-Sim for Highly Cluttered Environments via Physics-Consistent Inter-Object Reasoning [11.05191602561784]
  Reconstructing physically valid 3D scenes from single-view observations is a prerequisite for bridging the gap between visual perception and robotic control.<n>We propose a novel physics-constrained Real-to-Sim pipeline that reconstructs physically consistent 3D scenes from single-view RGB-D data.
  arXiv  Detail & Related papers  (2026-02-13T05:24:58Z)
• GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed Materials [34.530526668727056]
  GaussianFluent is a framework for realistic simulation and rendering of dynamic object states.<n>It synthesizes interiors by densifying internal Gaussians guided by generative models.<n>It integrates an optimized Continuum Damage Material Point Method (CD-MPM) to enable brittle fracture simulation at remarkably high speed.
  arXiv  Detail & Related papers  (2026-01-14T07:59:52Z)
• PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis [37.21119648359889]
  PhysGM is a feed-forward framework that jointly predicts a 3D Gaussian representation and its physical properties from a single image.<n>Our method effectively generates high-fidelity 4D simulations from a single image in one minute.
  arXiv  Detail & Related papers  (2025-08-19T15:10:30Z)
• GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation [60.33467489955188]
  This paper studies the problem of estimating physical properties (system identification) through visual observations. To facilitate geometry-aware guidance in physical property estimation, we introduce a novel hybrid framework. We propose a new dynamic 3D Gaussian framework based on motion factorization to recover the object as 3D Gaussian point sets. In addition to the extracted object surfaces, the Gaussian-informed continuum also enables the rendering of object masks during simulations.
  arXiv  Detail & Related papers  (2024-06-21T07:37:17Z)
• Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video [58.043569985784806]
  We introduce latent intuitive physics, a transfer learning framework for physics simulation. It can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. We validate our model in three ways: (i) novel scene simulation with the learned visual-world physics, (ii) future prediction of the observed fluid dynamics, and (iii) supervised particle simulation.
  arXiv  Detail & Related papers  (2024-06-18T16:37:44Z)
• DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors [75.83647027123119]
  We propose to learn the physical properties of a material field with video diffusion priors.<n>We then utilize a physics-based Material-Point-Method simulator to generate 4D content with realistic motions.
  arXiv  Detail & Related papers  (2024-06-03T16:05:25Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering [41.589093951039814]
  We integrate physics-based animations of solids and fluids with 3D Gaussian Splatting (3DGS) to create novel effects in virtual scenes reconstructed using 3DGS. Our framework is capable of realistically reproducing surface highlights on dynamic fluids and facilitating interactions between scene objects and fluids from new views.
  arXiv  Detail & Related papers  (2024-01-27T06:45:22Z)
• DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation [81.11585774044848]
  We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
  arXiv  Detail & Related papers  (2023-10-11T05:34:36Z)
• Inferring Fluid Dynamics via Inverse Rendering [37.87293082992423]
  Humans have a strong intuitive understanding of physical processes such as fluid falling by just a glimpse of such a scene picture. This work achieves such a photo-to-fluid reconstruction functionality learned from unannotated videos.
  arXiv  Detail & Related papers  (2023-04-10T08:23:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.