GeoFunFlow-3D: A Physics-Guided Generative Flow Matching Framework for High-Fidelity 3D Aerodynamic Inference over Complex Geometries

• URL: http://arxiv.org/abs/2604.23350v1
• Date: Sat, 25 Apr 2026 15:24:13 GMT
• Title: GeoFunFlow-3D: A Physics-Guided Generative Flow Matching Framework for High-Fidelity 3D Aerodynamic Inference over Complex Geometries
• Abstract summary: GeoFunFlow-3D is a physics-guided generative flow matching framework.<n>We introduce a high-order discrete engine without automatic differentiation (No-AD) to reduce gradient stiffness.<n>For the NASA Rotor37 test, it accurately captures 3D detached shock structures.
• Score: 5.068156424858535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep generative models and neural operators have demonstrated significant potential for 3D aerodynamic inference. However, they often face inherent challenges in maintaining physical consistency and preserving high-frequency features, primarily due to spectral bias and gradient conflicts within the governing equations. To address these issues, we propose GeoFunFlow-3D, a physics-guided generative flow matching framework. Temporally, we utilize optimal transport theory to build the generation path, ensuring stable training dynamics. Spectrally, we introduce a high-order discrete engine without automatic differentiation (No-AD) to reduce gradient stiffness. Spatially, a topology-aware super-resolution module (SATO) is employed to rigorously enforce physical laws in localized regions such as shock waves. We evaluated our framework on complex industrial datasets. On the BlendedNet dataset, the model successfully avoids mode collapse even under sparse data conditions. For the NASA Rotor37 test, it accurately captures 3D detached shock structures. Compared to conventional operators, GeoFunFlow-3D significantly improves accuracy, reducing the pressure field error (RRMSE) to 0.0215 while maintaining competitive inference efficiency. Ultimately, this work provides a reliable, geometry-driven approach for generating high-dimensional fluid fields.

Related papers

• NanoMorph-3D: An End-to-End Physics-Driven Unrolling Framework for Nanomaterial Reconstruction [12.817808960536397]
  NanoMorph-3D is a unified end-to-end framework grounded in a comprehensive Nanomorphological taxonomy.<n>Powered by a large-scale synthetic dataset explicitly modeling non-linear electron attenuation, we design a Physics-Driven Unrolled Network mapping proximal gradient descent into a learnable architecture.<n> Experiments demonstrate NanoMorph-3D reconstructs diverse topologies with superior fidelity and speed.
  arXiv  Detail & Related papers  (2026-08-04T07:30:48Z)
• FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity [34.142288038459704]
  FlowObject is a framework that reformulates sparse-view 3D reconstruction as a training-free, guided inverse problem.<n>Our method significantly outperforms state-of-the-art generative models and optimization-based frameworks in both geometric completeness and view-dependent appearance fidelity.
  arXiv  Detail & Related papers  (2026-06-17T12:42:09Z)
• Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation [81.44955493339835]
  DeGO is a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation with factorized 4D foundation-model distillation.<n> Experiments on the Occ3D-NuScenes benchmark demonstrate that our method achieves state-of-the-art performance under weak supervision.
  arXiv  Detail & Related papers  (2026-05-27T15:09:55Z)
• Mesh Based Simulations with Spatial and Temporal awareness [2.867517731896504]
  We propose a unified framework to bridge the gap between geometric deep learning and rigorous numerical analysis.<n>We introduce three key innovations: (1) Multi Node Prediction, a stencil-level objective that predicts field values for a node's full local topology, enforcing spatial derivative consistency; (2) Temporal Correction, replacing unstable explicit schemes with a predictor-corrector via temporal Cross-Attention; and (3) Geometric Inductive Biases, leveraging 3D Rotary Positional Embeddings (RoPE) to robustly capture rotational symmetries in unstructured meshes.
  arXiv  Detail & Related papers  (2026-05-02T17:09:31Z)
• Attention-Guided Flow-Matching for Sparse 3D Geological Generation [7.734651455015875]
  3D-GeoFlow is the first Attention-Guided Continuous Flow Matching framework tailored for sparse multimodal geological modeling.<n>By reformulating discrete categorical generation as a simulation-free, continuous vector field regression, our model establishes stable, deterministic optimal transport paths.<n>To validate our framework, we curated a large-scale multimodal dataset comprising 2,200 procedurally generated 3D geological cases.
  arXiv  Detail & Related papers  (2026-04-07T07:02:53Z)
• Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation [3.697746606429496]
  We propose a differentiable physics framework for the quantitative 3D reconstruction of material properties from transient surface temperature measurements.<n>NeFTY parameterizes the 3D diffusivity field as a continuous neural field optimized through a rigorous numerical solver.<n>Our approach enforces thermodynamic laws as hard constraints while maintaining the memory efficiency required for high-resolution 3D tomography.
  arXiv  Detail & Related papers  (2026-03-11T17:59:42Z)
• PEST: Physics-Enhanced Swin Transformer for 3D Turbulence Simulation [19.744829080390165]
  Direct numerical simulation (DNS) offers the highest fidelity but is computationally prohibitive.<n>Existing data-driven alternatives struggle with stable long-horizon rollouts, physical consistency, and faithful simulation of small-scale structures.<n>We propose a Physics-Enhanced Swin Transformer (PEST) for 3D turbulence simulation.
  arXiv  Detail & Related papers  (2026-02-09T18:37:18Z)
• Robust Mesh Saliency GT Acquisition in VR via View Cone Sampling and Geometric Smoothing [59.12032628787018]
  3D mesh saliency ground truth is essential for human-centric visual modeling in virtual reality (VR)<n>Current VR eye-tracking pipelines rely on single ray sampling and Euclidean smoothing, triggering texture attention and signal leakage across gaps.<n>This paper proposes a robust framework to address these limitations.
  arXiv  Detail & Related papers  (2026-01-06T05:20:12Z)
• EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale [15.20548942455541]
  EddyFormer is a Transformer-based spectral-element architecture for large-scale turbulence simulation.<n>It achieves DNS-level accuracy at 2563 resolution, providing a 30x speedup over DNS.<n>It preserves accuracy on physics-invariant metrics-energy spectra, correlation functions, and structure functions-showing domain generalization.
  arXiv  Detail & Related papers  (2025-10-28T08:27:37Z)
• GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters [61.51810815162003]
  We propose an SE(3)-equivariant adapter framework ( GeoAda) that enables flexible and parameter-efficient fine-tuning for controlled generative tasks.<n>GeoAda preserves the model's geometric consistency while mitigating overfitting and catastrophic forgetting.<n>We demonstrate the wide applicability of GeoAda across diverse geometric control types, including frame control, global control, subgraph control, and a broad range of application domains.
  arXiv  Detail & Related papers  (2025-07-02T18:44:03Z)
• Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction [52.32698071488864]
  We propose Factorized Implicit Global Convolution (FIGConv), a novel architecture that efficiently solves CFD problems for very large 3D meshes.<n>FIGConv achieves quadratic complexity $O(N2)$, a significant improvement over existing 3D neural CFD models.<n>We validate our approach on the industry-standard Ahmed body dataset and the large-scale DrivAerNet dataset.
  arXiv  Detail & Related papers  (2025-02-06T18:57:57Z)
• Aero-Nef: Neural Fields for Rapid Aircraft Aerodynamics Simulations [1.1932047172700866]
  This paper presents a methodology to learn surrogate models of steady state fluid dynamics simulations on meshed domains. The proposed models can be applied directly to unstructured domains for different flow conditions. Remarkably, the method can perform inference five order of magnitude faster than the high fidelity solver on the RANS transonic airfoil dataset.
  arXiv  Detail & Related papers  (2024-07-29T11:48:44Z)
• 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)
• Geometry-Informed Neural Operator for Large-Scale 3D PDEs [76.06115572844882]
  We propose the geometry-informed neural operator (GINO) to learn the solution operator of large-scale partial differential equations. We successfully trained GINO to predict the pressure on car surfaces using only five hundred data points.
  arXiv  Detail & Related papers  (2023-09-01T16:59:21Z)
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles [60.12186997181117]
  Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements. We propose GeoMol, an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate 3D conformers.
  arXiv  Detail & Related papers  (2021-06-08T14:17:59Z)

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.