DeCoDE Lab

Dataverse of the DeCoDE lab at MIT.

Featured Dataverses

In order to use this feature you must have at least one published or linked dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

1 to 10 of 16 Results

Bike-Bench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints May 16, 2025 Regenwetter, Lyle; Abu Obaideh, Yazan; Chiotti, Fabien; Lykourentzou, Ioanna; Ahmed, Faez, 2025, "Bike-Bench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints", https://doi.org/10.7910/DVN/BSJSM6, Harvard Dataverse, V2, UNF:6:big+g1nsM76CzXnsqpqciw== [fileUNF] We introduce Bike-Bench, an engineering design benchmark for evaluating generative models on problems with multiple real-world objectives and constraints. As generative AI's reach continues to grow, evaluating its capability to understand physical laws, human guidelines, and hard constraints grows increasingly important. Engineering product design...
VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software May 15, 2025 Man, Brandon; Nehme, Ghadi; Alam, Md. Ferdous; Ahmed, Faez, 2025, "VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software", https://doi.org/10.7910/DVN/WX8PCK, Harvard Dataverse, V1 VideoCAD is a large-scale synthetic dataset consisting of over 41K annotated video recordings of CAD operations, generated using an automated framework for collecting high-fidelity UI action data from human-made CAD designs. Comparison with existing datasets shows that VideoCAD offers an order of magnitude higher complexity in UI interaction learni...
BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designs Mar 18, 2025 Regenwetter, Lyle; Abu Obaideh, Yazan; Heyrani Nobari; Ahmed, Faez, 2024, "BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designs", https://doi.org/10.7910/DVN/XMRBWN, Harvard Dataverse, V2 The dataset is comprised of 1.4 million procedurally-generated bicycle designs which are represented parametrically, as JSON files, and as rasterized images. The dataset is created through the use of a rendering engine which harnesses the BikeCAD software to generate vector graphics from parametric designs. This rendering engine is discussed in the...
DrivAerNet++: Annotations Feb 22, 2025 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks Elrefaie, Mohamed, 2025, "DrivAerNet++: Annotations", https://doi.org/10.7910/DVN/CAWRXI, Harvard Dataverse, V1 In addition to the CFD simulation data, our dataset includes detailed annotations for various car components (29 labels), such as wheels, side mirrors, and doors. These annotations are instrumental for a range of machine learning tasks, including classification, semantic segmentation, and object detection. The comprehensive labeling can also facili...
DrivAerNet++: Wall Shear Stress Feb 6, 2025 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks Elrefaie, Mohamed; Morar, Florin; Dai, Angela; Ahmed, Faez, 2024, "DrivAerNet++: Wall Shear Stress", https://doi.org/10.7910/DVN/PCZYL4, Harvard Dataverse, V2 The VTK files contain high-fidelity wall shear stress data on the surfaces of various industry-standard car designs, capturing essential aerodynamic characteristics. Each file provides the wall shear stress distribution across different car body types (fastback, notchback, estateback), underbody designs (smooth and detailed), and wheel configuratio...
DrivAerNet++: CFD Nov 19, 2024 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks Elrefaie, Mohamed; Morar, Florin; Ahmed, Faez; Dai, Angela, 2024, "DrivAerNet++: CFD", https://doi.org/10.7910/DVN/EEYHUA, Harvard Dataverse, V1 The VTK files contain volumetric CFD data, including pressure, velocity fields, and wall shear stresses, for various industry-standard car designs. Each file provides a detailed representation of the aerodynamic flow around different car body types (fastback, notchback, estateback), underbody designs (smooth and detailed), and wheel configurations,...
DrivAerNet++: Pressure Nov 19, 2024 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks Elrefaie, Mohamed; Ahmed, Faez; Dai, Angela; Morar, Florin, 2024, "DrivAerNet++: Pressure", https://doi.org/10.7910/DVN/K7PWNJ, Harvard Dataverse, V1 The VTK files contain high-fidelity pressure field data on the surfaces of various industry-standard car designs, capturing key aerodynamic features. Each file provides the pressure distribution across different car body types (fastback, notchback, estateback), underbody designs (smooth and detailed), and wheel configurations. Strict Licensing Noti...
DrivAerNet++: 3D Meshes Nov 19, 2024 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks Elrefaie, Mohamed; Ahmed, Faez; Dai, Angela; Morar, Florin, 2024, "DrivAerNet++: 3D Meshes", https://doi.org/10.7910/DVN/OYU2FG, Harvard Dataverse, V1 The folder contains industry-standard 3D meshes for all car designs in the DrivAerNet++ dataset. Each STL file represents a unique car geometry, including variations across different body types such as fastback, notchback, and estateback. Additionally, this folder includes models with diverse underbody configurations (smooth for electric cars and d...
DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks(MIT) Nov 19, 2024 The data for this project are stored on the Northeast Storage Exchange (NESE). Follow the instructions for large data download found on our website: Downloading data from NESE via Globus: Quick Start DrivAerNet++ is the first large-scale, high-fidelity multimodal dataset of its kind, featuring over 8,000 industry-standard car designs with diverse c...
DATED: A Dataset of Centrifugal Compressors [Metadata] Jul 19, 2024 Picard, Cyril; Schiffman, Jürg; Ahmed, Faez, 2024, "DATED: A Dataset of Centrifugal Compressors [Metadata]", https://doi.org/10.7910/DVN/O8OE6N, Harvard Dataverse, V1 Dataset of 22 million centrifugal compressors with their performance predicted by a 1D mean-line analysis model. The dataset was generated to discuss guidelines for generating synthetic datasets for engineering design. However, it can also be used to train pre-design tools for centrifugal compressors. The actual dataset is available on Zenodo (10.5...

Bike-Bench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints

May 16, 2025

Regenwetter, Lyle; Abu Obaideh, Yazan; Chiotti, Fabien; Lykourentzou, Ioanna; Ahmed, Faez, 2025, "Bike-Bench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints", https://doi.org/10.7910/DVN/BSJSM6, Harvard Dataverse, V2, UNF:6:big+g1nsM76CzXnsqpqciw== [fileUNF]

We introduce Bike-Bench, an engineering design benchmark for evaluating generative models on problems with multiple real-world objectives and constraints. As generative AI's reach continues to grow, evaluating its capability to understand physical laws, human guidelines, and hard constraints grows increasingly important. Engineering product design...

VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software

May 15, 2025

Man, Brandon; Nehme, Ghadi; Alam, Md. Ferdous; Ahmed, Faez, 2025, "VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software", https://doi.org/10.7910/DVN/WX8PCK, Harvard Dataverse, V1

VideoCAD is a large-scale synthetic dataset consisting of over 41K annotated video recordings of CAD operations, generated using an automated framework for collecting high-fidelity UI action data from human-made CAD designs. Comparison with existing datasets shows that VideoCAD offers an order of magnitude higher complexity in UI interaction learni...

BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designs

Mar 18, 2025

Regenwetter, Lyle; Abu Obaideh, Yazan; Heyrani Nobari; Ahmed, Faez, 2024, "BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designs", https://doi.org/10.7910/DVN/XMRBWN, Harvard Dataverse, V2

The dataset is comprised of 1.4 million procedurally-generated bicycle designs which are represented parametrically, as JSON files, and as rasterized images. The dataset is created through the use of a rendering engine which harnesses the BikeCAD software to generate vector graphics from parametric designs. This rendering engine is discussed in the...

DrivAerNet++: Annotations

Feb 22, 2025 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Elrefaie, Mohamed, 2025, "DrivAerNet++: Annotations", https://doi.org/10.7910/DVN/CAWRXI, Harvard Dataverse, V1

In addition to the CFD simulation data, our dataset includes detailed annotations for various car components (29 labels), such as wheels, side mirrors, and doors. These annotations are instrumental for a range of machine learning tasks, including classification, semantic segmentation, and object detection. The comprehensive labeling can also facili...

DrivAerNet++: Wall Shear Stress

Feb 6, 2025 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Elrefaie, Mohamed; Morar, Florin; Dai, Angela; Ahmed, Faez, 2024, "DrivAerNet++: Wall Shear Stress", https://doi.org/10.7910/DVN/PCZYL4, Harvard Dataverse, V2

The VTK files contain high-fidelity wall shear stress data on the surfaces of various industry-standard car designs, capturing essential aerodynamic characteristics. Each file provides the wall shear stress distribution across different car body types (fastback, notchback, estateback), underbody designs (smooth and detailed), and wheel configuratio...

DrivAerNet++: CFD

Nov 19, 2024 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Elrefaie, Mohamed; Morar, Florin; Ahmed, Faez; Dai, Angela, 2024, "DrivAerNet++: CFD", https://doi.org/10.7910/DVN/EEYHUA, Harvard Dataverse, V1

The VTK files contain volumetric CFD data, including pressure, velocity fields, and wall shear stresses, for various industry-standard car designs. Each file provides a detailed representation of the aerodynamic flow around different car body types (fastback, notchback, estateback), underbody designs (smooth and detailed), and wheel configurations,...

DrivAerNet++: Pressure

Nov 19, 2024 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Elrefaie, Mohamed; Ahmed, Faez; Dai, Angela; Morar, Florin, 2024, "DrivAerNet++: Pressure", https://doi.org/10.7910/DVN/K7PWNJ, Harvard Dataverse, V1

The VTK files contain high-fidelity pressure field data on the surfaces of various industry-standard car designs, capturing key aerodynamic features. Each file provides the pressure distribution across different car body types (fastback, notchback, estateback), underbody designs (smooth and detailed), and wheel configurations. Strict Licensing Noti...

DrivAerNet++: 3D Meshes

Nov 19, 2024 - DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Elrefaie, Mohamed; Ahmed, Faez; Dai, Angela; Morar, Florin, 2024, "DrivAerNet++: 3D Meshes", https://doi.org/10.7910/DVN/OYU2FG, Harvard Dataverse, V1

The folder contains industry-standard 3D meshes for all car designs in the DrivAerNet++ dataset. Each STL file represents a unique car geometry, including variations across different body types such as fastback, notchback, and estateback. Additionally, this folder includes models with diverse underbody configurations (smooth for electric cars and d...

DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks(MIT)

Nov 19, 2024

The data for this project are stored on the Northeast Storage Exchange (NESE). Follow the instructions for large data download found on our website: Downloading data from NESE via Globus: Quick Start DrivAerNet++ is the first large-scale, high-fidelity multimodal dataset of its kind, featuring over 8,000 industry-standard car designs with diverse c...

DATED: A Dataset of Centrifugal Compressors [Metadata]

Jul 19, 2024

Picard, Cyril; Schiffman, Jürg; Ahmed, Faez, 2024, "DATED: A Dataset of Centrifugal Compressors [Metadata]", https://doi.org/10.7910/DVN/O8OE6N, Harvard Dataverse, V1

Dataset of 22 million centrifugal compressors with their performance predicted by a 1D mean-line analysis model. The dataset was generated to discuss guidelines for generating synthetic datasets for engineering design. However, it can also be used to train pre-design tools for centrifugal compressors. The actual dataset is available on Zenodo (10.5...

Add Data

Share Dataverse

Link Dataverse

Reset Modifications