arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.11207cs.CVcs.AIcs.CE
收藏

关于使用扩散模型生成合理设计的噪声调度研究

On the Noise Scheduling for Generating Plausible Designs with Diffusion Models

BMW Group(宝马集团);LIACS, Leiden University(莱顿大学LIACS学院)

Jiajie Fan, Laure Vuaille, Thomas Bäck, Hao Wang

AI总结:

本文研究扩散模型噪声调度对结构设计合理性的影响,提出两种确定噪声范围的技术及新型参数化噪声调度,应用于 EDM 模型后,将合理设计比率提升至 93.5% 并显著改善 FID。

摘要:

深度生成模型(DGMs)被广泛用于在从时尚到汽车等多个行业创建创新设计。除了生成高视觉质量的图像外,结构设计生成任务对语义表达施加了更严格的约束,例如没有悬浮材料或缺失部件,我们在本文中将其称为合理性。我们深入探讨了扩散模型的噪声调度对结果合理性的影响:存在一个噪声水平范围,在该范围内模型的性能决定了结果的合理性。此外,我们提出了两种技术来确定给定图像集的该范围,并设计了一种新颖的参数化噪声调度以获得更好的合理性。我们将此噪声调度应用于著名扩散模型 EDM 的训练和采样,并将其与其默认噪声调度进行比较。与 EDM 相比,我们的调度将合理设计的比率从 83.4% 显著提高到 93.5%,Fréchet Inception Distance(FID)从 7.84 改善至 4.87。先进图像编辑工具的进一步应用证明了模型对结构的扎实理解。

英文摘要:

Deep Generative Models (DGMs) are widely used to create innovative designs across multiple industries, ranging from fashion to the automotive sector. In addition to generating images of high visual quality, the task of structural design generation imposes more stringent constrains on the semantic expression, e.g., no floating material or missing part, which we refer to as plausibility in this work. We delve into the impact of noise schedules of diffusion models on the plausibility of the outcome: there exists a range of noise levels at which the model's performance decides the result plausibility. Also, we propose two techniques to determine such a range for a given image set and devise a novel parametric noise schedule for better plausibility. We apply this noise schedule to the training and sampling of the well-known diffusion model EDM and compare it to its default noise schedule. Compared to EDM, our schedule significantly improves the rate of plausible designs from 83.4% to 93.5% and Fréchet Inception Distance (FID) from 7.84 to 4.87. Further applications of advanced image editing tools demonstrate the model's solid understanding of structure.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑