GeoCAD: Local Geometry-Controllable CAD Generation
By: Zhanwei Zhang , Kaiyuan Liu , Junjie Liu and more
Potential Business Impact:
Changes computer designs using text instructions.
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.
Similar Papers
GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image
CV and Pattern Recognition
Turns drawings into 3D models for building.
CAD-Coder:Text-Guided CAD Files Code Generation
Graphics
Lets you tell computers to draw anything you want.
GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancing
Graphics
Builds 3D models from messy scans automatically.