Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder

arXiv:2403.05352v1 Announce Type: new
Abstract: 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 …

abstract arxiv autoencoder cs.cv deep generative models denoising design designers designs evaluation focus generated generative generative design generative models human images metrics quality type visual