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

TL;DR

SldprtNet is a comprehensive large-scale multimodal dataset of industrial parts designed to advance semantic-driven CAD modeling and 3D design through multimodal learning, including images, text, and 3D models.

Contribution

The paper introduces SldprtNet, a novel multimodal dataset with tools for scalable dataset expansion, supporting diverse modalities and facilitating research in language-driven 3D CAD generation.

Findings

Multimodal inputs improve CAD generation accuracy.

Fine-tuning on the dataset enhances model performance.

The dataset supports diverse industrial part representations.

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.