A great interest has arisen in using Deep Generative Models (DGM) for generative design. When assessing the quality of the generated designs, human designers focus more on structural plausibility, e.g., no missing component, rather than visual artifacts, e.g., noises in the images. Meanwhile, commonly used metrics such as Fr\'echet Inception Distance (FID) may not evaluate accurately as they tend to penalize visual artifacts instead of structural implausibility. As such, FID might not be suitable to assess the performance of DGMs for a generative design task. In this work, we propose to encode the input designs with a simple Denoising Autoencoder (DAE) and measure the distribution distance in the latent space thereof. We experimentally test our DAE-based metrics with FID and other state-of-the-art metrics on three data sets: compared to FID and some more recent works, e.g., FD$_\text{DINO-V2}$ and topology distance, DAE-based metrics can effectively detect implausible structures and are more consistent with structural inspection by human experts.

翻译：近年来，深度生成模型在生成式设计中引起了广泛关注。在评估生成设计的质量时，人类设计师更关注结构合理性（例如无缺失组件），而非视觉伪影（例如图像噪声）。与此同时，常用评估指标如弗雷歇初始距离（Fréchet Inception Distance，FID）可能无法准确评估，因其倾向于惩罚视觉伪影而非结构不合理性。因此，FID可能不适用于评估生成式设计任务中深度生成模型的性能。本研究提出使用简单的去噪自编码器对输入设计进行编码，并测量其潜在空间中的分布距离。我们在三个数据集上通过FID及其他最新指标对基于去噪自编码器的指标进行实验测试：与FID及近期研究（如FD$_\text{DINO-V2}$和拓扑距离）相比，基于去噪自编码器的指标能够有效检测不合理结构，且与人类专家的结构检查结果更为一致。