Representation Learning for Sequential Volumetric Design Tasks
Journal of Mechanical Design · 01.05.2025 · 147 (5)
DOI: 10.1115/1.4066686 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 18.11.2024. Verfasst von Md Ferdous Alam und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben.
Abstract (Originalsprache)
Volumetric design, also called massing design, is the first and critical step in professional building design, which is sequential in nature. As the volumetric design process requires careful design decisions and iterative adjustments, the underlying sequential design process encodes valuable information for designers. Many efforts have been made to automatically generate reasonable volumetric designs, but the quality of the generated design solutions varies, and evaluating a design solution requires either a prohibitively comprehensive set of metrics or expensive human expertise. While previous approaches focused on learning only the final design instead of sequential design tasks, we propose to encode the design knowledge from a collection of expert or high-performing design sequences and extract useful representations using transformer-based models. Later we propose to utilize the learned representations for crucial downstream applications such as design preference evaluation and procedural design generation. We develop the preference model by estimating the density of the learned representations, whereas we train an autoregressive transformer model for sequential design generation. We demonstrate our ideas by leveraging a novel dataset of thousands of sequential volumetric designs. Our preference model can compare two arbitrarily given design sequences and is almost 90% accurate in evaluation against random design sequences. Our autoregressive model is also capable of autocompleting a volumetric design sequence from a partial design sequence.
Zitieren
APA
Alam, M. F., Wang, Y., Cheng, C., & Luo, J. (2025). Representation Learning for Sequential Volumetric Design Tasks. Journal of Mechanical Design, 147(5). https://doi.org/10.1115/1.4066686
Vancouver
Alam MF, Wang Y, Cheng C, Luo J. Representation Learning for Sequential Volumetric Design Tasks. Journal of Mechanical Design. 2025;147(5). doi:10.1115/1.4066686
BibTeX
@article{Alam2025,
author = {Alam, Md Ferdous and Wang, Yi and Cheng, Chin-Yi and Luo, Jieliang},
title = {Representation Learning for Sequential Volumetric Design Tasks},
journal = {Journal of Mechanical Design},
year = {2025},
volume = {147},
number = {5},
doi = {10.1115/1.4066686}
}
EUVIMED