GeoFusion-CAD: Structure-Aware Diffusion with Geometric State Space for Parametric 3D Design

TL;DR

GeoFusion-CAD introduces a hierarchical, structure-aware diffusion model for scalable, long-sequence parametric 3D CAD generation, outperforming transformer-based methods in fidelity and consistency.

Contribution

The paper presents a novel diffusion framework encoding CAD programs as hierarchical trees with a state-space process, enabling scalable, long-range structural dependency modeling.

Findings

Outperforms transformer models on long sequences

Maintains high geometric fidelity and topological consistency

Sets new state-of-the-art scores for long-sequence CAD generation

Abstract

Parametric Computer-Aided Design (CAD) is fundamental to modern 3D modeling, yet existing methods struggle to generate long command sequences, especially under complex geometric and topological dependencies. Transformer-based architectures dominate CAD sequence generation due to their strong dependency modeling, but their quadratic attention cost and limited context windowing hinder scalability to long programs. We propose GeoFusion-CAD, an end-to-end diffusion framework for scalable and structure-aware generation. Our proposal encodes CAD programs as hierarchical trees, jointly capturing geometry and topology within a state-space diffusion process. Specifically, a lightweight C-Mamba block models long-range structural dependencies through selective state transitions, enabling coherent generation across extended command sequences. To support long-sequence evaluation, we introduce DeepCAD-240, an extended benchmark that increases the sequence length ranging from 40 to 240 while preserving sketch-extrusion semantics from the ABC dataset. Extensive experiments demonstrate that GeoFusion-CAD achieves superior performance on both short and long command ranges, maintaining high geometric fidelity and topological consistency where Transformer-based models degrade. Our approach sets new state-of-the-art scores for long-sequence parametric CAD generation, establishing a scalable foundation for next-generation CAD modeling systems. Code and datasets are available at GitHub.