CVGRMar 23

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

arXiv:2603.2197823.9h-index: 3
AI Analysis

This addresses scalability issues in CAD modeling for designers and engineers, though it appears incremental as it builds on existing diffusion and state-space methods.

The paper tackles the problem of generating long command sequences in parametric CAD modeling, which existing methods struggle with due to complex dependencies, and proposes GeoFusion-CAD, a diffusion framework that achieves superior performance on both short and long sequences, setting new state-of-the-art scores.

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.

Foundations

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

Your Notes