CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
Yu Yuan, Shizhao Sun, Qi Liu, Jiang Bian

TL;DR
CAD-Editor is a novel framework for text-based CAD editing that combines automated data synthesis and a locate-then-infill approach, enabling effective modification of CAD models guided by textual instructions.
Contribution
It introduces the first text-based CAD editing framework with an automated data synthesis pipeline and a locate-then-infill methodology leveraging large language models.
Findings
Achieves superior quantitative performance
Demonstrates effective qualitative editing results
Automated data synthesis reduces training data requirements
Abstract
Computer Aided Design (CAD) is indispensable across various industries. \emph{Text-based CAD editing}, which automates the modification of CAD models based on textual instructions, holds great potential but remains underexplored. Existing methods primarily focus on design variation generation or text-based CAD generation, either lacking support for text-based control or neglecting existing CAD models as constraints. We introduce \emph{CAD-Editor}, the first framework for text-based CAD editing. To address the challenge of demanding triplet data with accurate correspondence for training, we propose an automated data synthesis pipeline. This pipeline utilizes design variation models to generate pairs of original and edited CAD models and employs Large Vision-Language Models (LVLMs) to summarize their differences into editing instructions. To tackle the composite nature of text-based CAD…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsModel-Driven Software Engineering Techniques
