cs.ROMar 13, 2026

SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Design

Authors: Ruogu Li, Sikai Li, Yao Mu, Mingyu Ding

Organizations: University of North Carolina at Chapel Hill · Shanghai Jiao Tong University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

We introduce SldprtNet, a large-scale dataset comprising over 242,000 industrial parts, designed for semantic-driven CAD modeling, geometric deep learning, and the training and fine-tuning of multimodal models for 3D design. The dataset provides 3D models in both .step and .sldprt formats to support diverse training and testing. To enable parametric modeling and facilitate dataset scalability, we developed supporting tools, an encoder and a decoder, which support 13 types of CAD commands and enable lossless transformation between 3D models and a structured text representation. Additionally, each sample is paired with a composite image created by merging seven rendered views from different viewpoints of the 3D model, effectively reducing input token length and accelerating inference. By combining this image with the parameterized text output from the encoder, we employ the lightweight multimodal language model Qwen2.5-VL-7B to generate a natural language description of each part's appearance and functionality. To ensure accuracy, we manually verified and aligned the generated descriptions, rendered images, and 3D models. These descriptions, along with the parameterized modeling scripts, rendered images, and 3D model files, are fully aligned to construct SldprtNet. To assess its effectiveness, we fine-tuned baseline models on a dataset subset, comparing image-plus-text inputs with text-only inputs. Results confirm the necessity and value of multimodal datasets for CAD generation. It features carefully selected real-world industrial parts, supporting tools for scalable dataset expansion, diverse modalities, and ensured diversity in model complexity and geometric features, making it a comprehensive multimodal dataset built for semantic-driven CAD modeling and cross-modal learning.

Figures & tables

DatasetSldprtNetABCShapeNetModelNetFusion 360Thingi10K
Models242,6061,000,000+3,000,000+151,12850,000+10,000
FormatSldprtB-RepMeshMeshB-RepMesh
Parametric✓✓×\times×\times✓×\times
Multi-view✓×\times✓×\times×\times×\times
Reconstructable✓×\times×\times×\times×\times×\times
Model Description✓×\times×\times×\times×\times×\times
TABLE I: Comparative Overview of Major CAD and 3D Model Datasets
Fig. 1: Overview of SldprtNet dataset.
Fig. 2: Twenty randomly sampled CAD parts from SldprtNet, illustrating its industrial orientation and geometric diversity across varied mechanical components.
Fig. 3: Overview of the automated data processing pipeline for constructing SldprtNet.
Fig. 4: Distribution of CAD model complexity in the SldprtNet dataset based on the number of feature operations per part. The chart presents four complexity levels with their corresponding proportions and sample counts.
Fig. 5: Distribution of CAD features and total counts in the SldprtNet dataset. The figure summarizes the usage frequency of 13 parametric operations across all parts.
 
Feature Tree:
Top View (RefPlane)
Sketch1 (ProfileFeature)
Extrude1 (Extrusion)
- Sketch: Sketch1
FeatureName: Top View Type: RefPlane
TABLE II: Example of Parametric Text Representation
MetricQwen2.5-7BQwen2.5-7B-VL
Exact Match Score0.00580.0099
BLEU Score97.182797.9309
Test Samples36443644
Command-Level F10.32470.3670
Tolerance Accuracy0.50160.4630
Partial Match Rate0.55540.6162
TABLE III: Baseline Model Performance Comparison
Fig. 6: Composite image of a CAD model from seven standard views, including top, bottom, left, right, front, back, and isometric.
More in this topic

Text-to-CAD Generation

Text-to-CAD generation turns natural-language design intent into executable, editable parametric 3D models and assemblies.

See all 48 papers

Explore similar work

CardsList
Jun 5, 2026

GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding

Multi-modal approaches used for 3D CAD generation require substantial computational resources, necessitating efficient training. To address this, we propose GuideCAD, which leverages semantically rich visual-textual representations having only a small number of trainable parameters to generate 3D CAD models. Specifically, GuideCAD uses a mapping network that converts image embeddings into prefix embeddings, enabling a pretrained large language model to integrate visual and textual information. As a result, a transformer-based decoder predicts the construction sequence using the visual-textual embeddings in order to generate the 3D CAD model. For experimental evaluation, we construct a new dataset, referred to as GuideCAD, which consists of text-image pairs. Each pair includes a text prompt that represents a 3D CAD construction sequence and its corresponding 3D CAD image. Our experimental results show that GuideCAD generates comparably high-quality 3D CAD models while using approximately four times fewer parameters and achieving twice the training efficiency compared to fine-tuning approaches. We have released the source code and dataset for our method at: https://github.com/mskimS2/GuideCAD

Minseong Kim, Jinyeong Park, Sungho Park +1

Convergence Research Center for Insect Vectors Incheon, South Korea · Department of Computer Science and Engineering Incheon National University Incheon, 22012, South Korea · Department of Computer Science and Engineering Center for Brain-Machine Interface Incheon National University Incheon, South Korea

3D Asset GenerationParametric CAD ModelingPrompt TuningMultimodal GenerationText-to-CAD GenerationPrefix Tuning
AskPDF
Mar 5, 2026

DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces

Computer-Aided Design (CAD) relies on structured and editable geometric representations, yet existing generative methods are constrained by small annotated datasets with explicit design histories or boundary representation (BRep) labels. Meanwhile, millions of unannotated 3D meshes remain untapped, limiting progress in scalable CAD generation. To address this, we propose DreamCAD, a multi-modal generative framework that directly produces editable BReps from point-level supervision, without CAD-specific annotations. DreamCAD represents each BRep as a set of parametric patches (e.g., Bézier surfaces) and uses a differentiable tessellation method to generate meshes. This enables large-scale training on 3D datasets while reconstructing connected and editable surfaces. Furthermore, we introduce CADCap-1M, the largest CAD captioning dataset to date, with 1M+ descriptions generated using GPT-5 for advancing text-to-CAD research. DreamCAD achieves state-of-the-art performance on ABC and Objaverse benchmarks across text, image, and point modalities, improving geometric fidelity and surpassing 75% user preference. Code and dataset will be publicly available.

Mohammad Sadil Khan, Muhammad Usama, Rolandos Alexandros Potamias +4

DFKI, Germany · RPTU Kaiserslautern, Germany · Imperial College London, United Kingdom +1

Text-to-CAD GenerationParametric CAD Modeling
AskPDF
May 11, 2026

BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD

Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond recognizing the outer shape of a part, this task involves understanding its 3D structure, inferring engineering parameters, and choosing CAD operations that reflect how the part would be designed and manufactured. Despite the promise of Multimodal large language models (MLLMs) for this task, they are rarely evaluated on whether these capabilities jointly hold in realistic industrial CAD settings. We present BenchCAD, a unified benchmark for industrial CAD reasoning. BenchCAD contains 17,900 execution-verified CadQuery programs across 106 industrial part families, including bevel gears, compression springs, twist drills, and other reusable engineering designs. It evaluates models through visual question answering, code question answering, image-to-code generation, and instruction-guided code editing, enabling fine-grained analysis across perception, parametric abstraction, and executable program synthesis. Across 10+ frontier models, BenchCAD shows that current systems often recover coarse outer geometry but fail to produce faithful parametric CAD programs. Common failures include missing fine 3D structure, misinterpreting industrial design parameters, and replacing essential operations such as sweeps, lofts, and twist-extrudes with simpler sketch-and-extrude patterns. Fine-tuning and reinforcement learning improve in-distribution performance, but generalization to unseen part families remains limited. These results position BenchCAD as a benchmark for measuring and improving the industrial readiness of multimodal CAD automation.

Haozhe Zhang, Kaichen Liu, Miaomiao Chen +4

University of Virginia · University of California, San Diego · Rice University

Benchmark ConstructionParametric CAD ModelingText-to-CAD GenerationCode Generation Benchmarks
AskPDF