CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM

TL;DR

CAD-MLLM is a pioneering multimodal system that generates parametric CAD models conditioned on diverse inputs like text, images, and point clouds, utilizing a new comprehensive dataset and advanced alignment techniques.

Contribution

The paper introduces CAD-MLLM, the first system to unify multimodal inputs for CAD generation, supported by the novel Omni-CAD dataset and specialized evaluation metrics.

Findings

Outperforms existing conditional generative methods

Robust to noise and missing data

Achieves high-quality topology and surface enclosure

Abstract

This paper aims to design a unified Computer-Aided Design (CAD) generation system that can easily generate CAD models based on the user's inputs in the form of textual description, images, point clouds, or even a combination of them. Towards this goal, we introduce the CAD-MLLM, the first system capable of generating parametric CAD models conditioned on the multimodal input. Specifically, within the CAD-MLLM framework, we leverage the command sequences of CAD models and then employ advanced large language models (LLMs) to align the feature space across these diverse multi-modalities data and CAD models' vectorized representations. To facilitate the model training, we design a comprehensive data construction and annotation pipeline that equips each CAD model with corresponding multimodal data. Our resulting dataset, named Omni-CAD, is the first multimodal CAD dataset that contains textual description, multi-view images, points, and command sequence for each CAD model. It contains approximately 450K instances and their CAD construction sequences. To thoroughly evaluate the quality of our generated CAD models, we go beyond current evaluation metrics that focus on reconstruction quality by introducing additional metrics that assess topology quality and surface enclosure extent. Extensive experimental results demonstrate that CAD-MLLM significantly outperforms existing conditional generative methods and remains highly robust to noises and missing points. The project page and more visualizations can be found at: https://cad-mllm.github.io/