CVJun 12, 2025

GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models

arXiv:2506.10337v23 citationsh-index: 7Has Code
Originality Incremental advance
AI Analysis

This addresses the need for efficient and user-friendly CAD design automation, particularly for modifying local parts with precise geometric constraints, though it is incremental as it builds on existing LLM and captioning techniques.

The paper tackles the problem of local geometry-controllable CAD generation by introducing GeoCAD, a method that uses large language models to modify local parts of CAD models based on user-specific geometric instructions, achieving high generation quality, validity, and text-to-CAD consistency as demonstrated in experiments.

Local geometry-controllable computer-aided design (CAD) generation aims to modify local parts of CAD models automatically, enhancing design efficiency. It also ensures that the shapes of newly generated local parts follow user-specific geometric instructions (e.g., an isosceles right triangle or a rectangle with one corner cut off). However, existing methods encounter challenges in achieving this goal. Specifically, they either lack the ability to follow textual instructions or are unable to focus on the local parts. To address this limitation, we introduce GeoCAD, a user-friendly and local geometry-controllable CAD generation method. Specifically, we first propose a complementary captioning strategy to generate geometric instructions for local parts. This strategy involves vertex-based and VLLM-based captioning for systematically annotating simple and complex parts, respectively. In this way, we caption $\sim$221k different local parts in total. In the training stage, given a CAD model, we randomly mask a local part. Then, using its geometric instruction and the remaining parts as input, we prompt large language models (LLMs) to predict the masked part. During inference, users can specify any local part for modification while adhering to a variety of predefined geometric instructions. Extensive experiments demonstrate the effectiveness of GeoCAD in generation quality, validity and text-to-CAD consistency. Code will be available at https://github.com/Zhanwei-Z/GeoCAD.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes