CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics

• URL: http://arxiv.org/abs/2512.07847v1
• Date: Tue, 25 Nov 2025 21:53:43 GMT
• Title: CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics
• Authors: Mohamed Elrefaie, Dule Shu, Matt Klenk, Faez Ahmed,
• Abstract summary: CarBench is the first comprehensive benchmark dedicated to large-scale 3D car aerodynamics.<n>We evaluate state-of-the-art models on DrivAerNet++, the largest public dataset for automotive aerodynamics.<n>To accelerate progress in data-driven engineering, we open-source the benchmark framework.
• Score: 5.362190317243247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving algorithmic innovation through standardized datasets and reproducible evaluation protocols. The growing availability of large-scale Computational Fluid Dynamics (CFD) datasets has opened new opportunities for applying machine learning to aerodynamic and engineering design. Yet, despite this progress, there exists no standardized benchmark for large-scale numerical simulations in engineering design. In this work, we introduce CarBench, the first comprehensive benchmark dedicated to large-scale 3D car aerodynamics, performing a large-scale evaluation of state-of-the-art models on DrivAerNet++, the largest public dataset for automotive aerodynamics, containing over 8,000 high-fidelity car simulations. We assess eleven architectures spanning neural operator methods (e.g., Fourier Neural Operator), geometric deep learning (PointNet, RegDGCNN, PointMAE, PointTransformer), transformer-based neural solvers (Transolver, Transolver++, AB-UPT), and implicit field networks (TripNet). Beyond standard interpolation tasks, we perform cross-category experiments in which transformer-based solvers trained on a single car archetype are evaluated on unseen categories. Our analysis covers predictive accuracy, physical consistency, computational efficiency, and statistical uncertainty. To accelerate progress in data-driven engineering, we open-source the benchmark framework, including training pipelines, uncertainty estimation routines based on bootstrap resampling, and pretrained model weights, establishing the first reproducible foundation for large-scale learning from high-fidelity CFD simulations, available at https://github.com/Mohamedelrefaie/CarBench.

Related papers

• Car Drag Coefficient Prediction from 3D Point Clouds Using a Slice-Based Surrogate Model [0.6882042556551609]
  This paper introduces a novel lightweight surrogate model for the prediction of the aerodynamic drag coefficient (Cd) based on a sequential slice-wise processing of the geometry of the 3D vehicle.<n>The model, trained and evaluated on the DrivAerNet++ dataset, achieves a high coefficient of determination (R2 > 0.9528) and a low mean absolute error (MAE approx 6.046 x 10-3) in Cd prediction.
  arXiv  Detail & Related papers  (2026-01-05T13:41:20Z)
• DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization [17.541117004160892]
  Traditional approaches face an intractable trade-off: computationally expensive Computational Dynamics (CFD) simulations generated weeks per design iteration, or simplified models that sacrifice production-grade accuracy.<n>DrivAerStar is the first dataset bridging academic machine learning research and industrial CFD practice, establishing a new standard for data-driven aerodynamic optimization in automotive development.<n>Beyond automotive applications, DrivAerStar demonstrates a paradigm for integrating high-fidelity physics simulations with Artificial Intelligence (AI) across engineering disciplines where computational constraints currently limit innovation.
  arXiv  Detail & Related papers  (2025-10-19T14:42:32Z)
• DrivAer Transformer: A high-precision and fast prediction method for vehicle aerodynamic drag coefficient based on the DrivAerNet++ dataset [1.184330339427731]
  This study proposes a point cloud learning framework called DrivAer Transformer.<n>The DAT structure uses the DrivAerNet++ dataset, which contains high-fidelity CFD data of industrial-standard 3D vehicle shapes.<n>The framework is expected to accelerate the vehicle design process and improve development efficiency.
  arXiv  Detail & Related papers  (2025-04-11T02:50:38Z)
• 3D Neural Operator-Based Flow Surrogates around 3D geometries: Signed Distance Functions and Derivative Constraints [3.100300350494905]
  computational cost of high-fidelity 3D flow simulations remains a significant challenge.<n>We evaluate Deep Operator Networks (DeepONet) and Geometric-DeepONet, a variant that incorporates geometry information via signed distance functions (SDFs)<n>Our results show that Geometric-DeepONet improves boundary-layer accuracy by up to 32% compared to standard DeepONet.
  arXiv  Detail & Related papers  (2025-03-21T16:40:48Z)
• DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks [25.00264553520033]
  DrivAerNet++ comprises 8,000 diverse car designs modeled with high-fidelity computational fluid dynamics (CFD) simulations.<n>The dataset includes diverse car configurations such as fastback, notchback, and estateback, with different underbody and wheel designs to represent both internal combustion engines and electric vehicles.<n>This dataset supports a wide array of machine learning applications including data-driven design optimization, generative modeling, surrogate model training, CFD simulation acceleration, and geometric classification.
  arXiv  Detail & Related papers  (2024-06-13T23:19:48Z)
• Bridging the Sim-to-Real Gap with Bayesian Inference [53.61496586090384]
  We present SIM-FSVGD for learning robot dynamics from data. We use low-fidelity physical priors to regularize the training of neural network models. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system.
  arXiv  Detail & Related papers  (2024-03-25T11:29:32Z)
• 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)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification [69.26747803963907]
  Rank-R Feedforward Neural Network (FNN) is a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters. First, it handles inputs as multilinear arrays, bypassing the need for vectorization, and can thus fully exploit the structural information along every data dimension. We establish the universal approximation and learnability properties of Rank-R FNN, and we validate its performance on real-world hyperspectral datasets.
  arXiv  Detail & Related papers  (2021-04-11T16:37:32Z)
• One-step regression and classification with crosspoint resistive memory arrays [62.997667081978825]
  High speed, low energy computing machines are in demand to enable real-time artificial intelligence at the edge. One-step learning is supported by simulations of the prediction of the cost of a house in Boston and the training of a 2-layer neural network for MNIST digit recognition. Results are all obtained in one computational step, thanks to the physical, parallel, and analog computing within the crosspoint array.
  arXiv  Detail & Related papers  (2020-05-05T08:00:07Z)

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.