用统一扩散模型生成更真实的CAD草图，同时处理连续参数与离散类别。
SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
- 通过高斯-软最大值扩散联合建模连续参数与离散类别。
- 在SketchGraphs数据集上FID降至7.80，NLL降至81.33，性能领先。
- 适合需要高质量参数化草图生成的工业设计与自动化建模场景。
我们提出SketchDNN，一种用于合成CAD草图的生成模型，通过统一的连续-离散扩散过程联合建模连续参数与离散类别标签。核心创新是高斯-软最大值扩散：对logits添加高斯噪声后，经软最大值映射到概率单纯形，实现离散变量的混合类别表示。该方法解决了两大挑战：原始参数化方式不一致以及草图中几何体的排列不变性问题。在SketchGraphs数据集上，生成质量显著提升，弗雷谢尔初始距离（FID）从16.04降至7.80，负对数似然（NLL）从84.8降至81.33，达到当前最佳水平。
原文摘要 · Abstract (English)
We present SketchDNN, a generative model for synthesizing CAD sketches that jointly models both continuous parameters and discrete class labels through a unified continuous-discrete diffusion process. Our core innovation is Gaussian-Softmax diffusion, where logits perturbed with Gaussian noise are projected onto the probability simplex via a softmax transformation, facilitating blended class labels for discrete variables. This formulation addresses 2 key challenges, namely, the heterogeneity of primitive parameterizations and the permutation invariance of primitives in CAD sketches. Our approach significantly improves generation quality, reducing Fréchet Inception Distance (FID) from 16.04 to 7.80 and negative log-likelihood (NLL) from 84.8 to 81.33, establishing a new state-of-the-art in CAD sketch generation on the SketchGraphs dataset.
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。