CVAIGRNov 5, 2024

FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models

arXiv:2411.05823v228 citationsh-index: 8Has CodeICLR
Originality Incremental advance
AI Analysis

This work addresses the need for more versatile and efficient CAD generation tools for designers and engineers, though it is incremental as it builds on existing LLM fine-tuning techniques.

The paper tackles the problem of limited controllability and inefficiency in existing controllable CAD generation methods by proposing FlexCAD, a unified model that fine-tunes large language models to generate CAD models across all construction hierarchies, achieving improved generation quality and controllability as demonstrated in experiments on a public dataset.

Recently, there is a growing interest in creating computer-aided design (CAD) models based on user intent, known as controllable CAD generation. Existing work offers limited controllability and needs separate models for different types of control, reducing efficiency and practicality. To achieve controllable generation across all CAD construction hierarchies, such as sketch-extrusion, extrusion, sketch, face, loop and curve, we propose FlexCAD, a unified model by fine-tuning large language models (LLMs). First, to enhance comprehension by LLMs, we represent a CAD model as a structured text by abstracting each hierarchy as a sequence of text tokens. Second, to address various controllable generation tasks in a unified model, we introduce a hierarchy-aware masking strategy. Specifically, during training, we mask a hierarchy-aware field in the CAD text with a mask token. This field, composed of a sequence of tokens, can be set flexibly to represent various hierarchies. Subsequently, we ask LLMs to predict this masked field. During inference, the user intent is converted into a CAD text with a mask token replacing the part the user wants to modify, which is then fed into FlexCAD to generate new CAD models. Comprehensive experiments on public dataset demonstrate the effectiveness of FlexCAD in both generation quality and controllability. Code will be available at https://github.com/microsoft/FlexCAD.

Code Implementations1 repo
Foundations

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

Your Notes