Target-Guided Bayesian Flow Networks for Quantitatively Constrained CAD Generation

TL;DR

This paper introduces Target-Guided Bayesian Flow Networks (TGBFN), a novel framework for generating multi-modal CAD sequences with quantitative constraints, achieving state-of-the-art results in fidelity and condition-awareness.

Contribution

TGBFN is the first model to handle multi-modal CAD data in a unified continuous space with guided Bayesian flow for property control.

Findings

Achieves state-of-the-art performance in constrained CAD generation

Handles multi-modality in a unified continuous space

Demonstrates high fidelity and condition-awareness

Abstract

Deep generative models, such as diffusion models, have shown promising progress in image generation and audio generation via simplified continuity assumptions. However, the development of generative modeling techniques for generating multi-modal data, such as parametric CAD sequences, still lags behind due to the challenges in addressing long-range constraints and parameter sensitivity. In this work, we propose a novel framework for quantitatively constrained CAD generation, termed Target-Guided Bayesian Flow Network (TGBFN). For the first time, TGBFN handles the multi-modality of CAD sequences (i.e., discrete commands and continuous parameters) in a unified continuous and differentiable parameter space rather than in the discrete data space. In addition, TGBFN penetrates the parameter update kernel and introduces a guided Bayesian flow to control the CAD properties. To evaluate TGBFN, we construct a new dataset for quantitatively constrained CAD generation. Extensive comparisons across single-condition and multi-condition constrained generation tasks demonstrate that TGBFN achieves state-of-the-art performance in generating high-fidelity, condition-aware CAD sequences. The code is available at https://github.com/scu-zwh/TGBFN.