Dataset zoo
Datasets
Datasets grouped by representation and task.
Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding
The field of Computer-Aided Design (CAD) generation has made significant progress in recent years. Existing methods typically fall into two separate categories: parametric CAD modeling and direct boundary representation (B-Rep) synthesis. I...
CV
Pointer-CAD
Constructing computer-aided design (CAD) models is labor-intensive but essential for engineering and manufacturing. Recent advances in Large Language Models (LLMs) have inspired the LLM-based CAD generation by representing CAD as command se...
CVCL
Img2CADSeq
Img2CADSeq uses a multi-stage pipeline with hierarchical codebook and VQ-Diffusion to generate CAD BRep sequences from single-view images, outperforming SOTA on new datasets.
CV
From Intent to Execution
Proposes CAD-RL, a multimodal Chain-of-Thought reinforcement learning framework for precise CAD code generation from natural language, with a new real-world dataset ExeCAD.
Text-to-CAD Evaluation with CADTests
Introduces CADTestBench, a test-based benchmark for evaluating Text-to-CAD models using executable software tests.
CVAILGRO
SHARP Challenge 2023
SHARP Challenge 2023 defines tracks, datasets, metrics, and baselines for CAD reverse engineering from point clouds and 3D scans.
BlenderLLM
BlenderLLM trains LLMs for CAD script generation via self-improvement, introducing BlendNet dataset and CADBench benchmark.
Physics-in-the-Loop
Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead of attempting to implicitly learn physical laws from data, we propose a Hybrid Agentic-...
CV
Masked BRep Autoencoder via Hierarchical Graph Transformer
We introduce a novel self-supervised learning framework that automatically learns representations from input computer-aided design (CAD) models for downstream tasks, including part classification, modeling segmentation, and machining featur...
GRLG
Extrusion Segmentation Strategy to improve CAD Reconstruction from Point Cloud
Computer-Aided Design is ubiquitous in todays world, as almost every manufactured object begins as a digital model across industries. At the same time, advances in 3D sensing have made point clouds a dominant form of raw 3D data. Recovering...
CVAI
Large Language Models for Computer-Aided Design (LLM4CAD) Fine-Tuned
Fine-tunes GPT-3.5 models on a new multimodal CAD dataset with text descriptions to improve text-to-CAD generation, evaluated via parsing rate and IoU.
Self-Supervised Representation Learning for CAD
Proposes self-supervised representation learning for CAD B-Rep geometry using a hybrid implicit/explicit surface, improving few-shot learning and achieving SOTA on benchmarks.
Text2CAD-Bench
Text-to-CAD generation aims to create parametric CAD models from natural language, enabling rapid prototyping and intuitive design workflows. However, existing benchmarks focus on basic primitives and simple sketch-extrude sequences, lackin...
LG
Pointer-CAD v2
Computer-aided design (CAD) plays a fundamental role in modern manufacturing by providing the high precision required for industrial production. Recent large language model based approaches formulate CAD generation as a sequence prediction ...
CV
A parametric and feature-based CAD dataset to support human-computer interaction for advanced 3D shape learning
A parametric and feature-based CAD dataset with a selection mechanism for human-computer interaction, enabling advanced 3D shape learning.
Revisiting CAD Model Generation by Learning Raster Sketch
Derived from paper: Revisiting CAD Model Generation by Learning Raster Sketch
CAD Translator
A novel encoder-decoder framework for text-to-parametric CAD generation using contrastive learning and fusion embeddings.
SketchGraphs
Introduces SketchGraphs, a large-scale dataset of 15 million parametric CAD sketches with geometric constraint graphs for machine learning.
Slice-100K
Derived from paper: Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing
Fusion 360 Gallery
Derived from paper: Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences (Reconstruction Dataset)
Automatic 3D CAD models reconstruction from 2D orthographic drawings
A two-stage method reconstructs 3D CAD models from 2D orthographic drawings using pattern-matching and loop detection, achieving 99.59% F-score.
Graph Representation of 3D CAD Models for Machining Feature Recognition With Deep Learning
Proposes a graph representation for 3D CAD models to enable deep learning-based machining feature recognition, outperforming voxel representations.
ArchCAD-400K
Derived from paper: ArchCAD-400K: An Open Large-Scale Architectural CAD Dataset and New Baseline for Panoptic Symbol Spotting
Sketch-graphs
Derived from paper: Sketch-graphs: A large-scale dataset for modeling relational geometry in computer-aided design
MF-UAVPose6D
For uncrewed aerial vehicles (UAVs), estimating six-degree-of-freedom (6-DoF) poses is essential for airspace situational awareness, target tracking, and counter-UAV operations. However, non-cooperative targets usually lack computer-aided d...
CVRO