用Mamba+与扩散模型生成复杂参数化设计长序列，突破工业级建模瓶颈。
MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence
- 融合Mamba+与Transformer的自编码器，提取多尺度潜在表示
- 在256步长的参数序列上实现最优重建与生成性能
- 适合需要长序列参数化设计的工业建模与自动化场景
参数化计算机辅助设计（CAD）在工业应用中至关重要，但现有方法难以生成受几何与拓扑约束影响的长序列参数命令。为此，我们提出MamTiff-CAD，一种基于Transformer扩散模型的多尺度潜在表示框架。设计新型自编码器，集成Mamba+与Transformer，将参数化CAD序列转换为潜在表示。Mamba+块引入遗忘门机制，有效捕捉长程依赖。非自回归Transformer解码器用于重建潜在表示。基于多尺度Transformer的扩散模型在这些潜在嵌入上训练，学习长序列命令分布。此外，我们构建了一个包含长参数序列的数据集，单个CAD模型最长可达256条命令。实验表明，MamTiff-CAD在重建与生成任务上均达到当前最优表现，验证了其在60至256步长的复杂参数化模型生成中的有效性。
原文摘要 · Abstract (English)
Parametric Computer-Aided Design (CAD) is crucial in industrial applications, yet existing approaches often struggle to generate long sequence parametric commands due to complex CAD models' geometric and topological constraints. To address this challenge, we propose MamTiff-CAD, a novel CAD parametric command sequences generation framework that leverages a Transformer-based diffusion model for multi-scale latent representations. Specifically, we design a novel autoencoder that integrates Mamba+ and Transformer, to transfer parameterized CAD sequences into latent representations. The Mamba+ block incorporates a forget gate mechanism to effectively capture long-range dependencies. The non-autoregressive Transformer decoder reconstructs the latent representations. A diffusion model based on multi-scale Transformer is then trained on these latent embeddings to learn the distribution of long sequence commands. In addition, we also construct a dataset that consists of long parametric sequences, which is up to 256 commands for a single CAD model. Experiments demonstrate that MamTiff-CAD achieves state-of-the-art performance on both reconstruction and generation tasks, confirming its effectiveness for long sequence (60-256) CAD model generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。