Representation Learning for Sequential Volumetric Design Tasks

TL;DR

This paper introduces a transformer-based approach to learn and utilize representations of sequential volumetric design tasks, enabling better evaluation and generation of building massing designs.

Contribution

It proposes a novel method to encode sequential volumetric design knowledge using transformers and applies it to design evaluation and generation tasks.

Findings

Preference model achieves nearly 90% accuracy in sequence comparison.

Autoregressive model successfully autocompletes design sequences.

Leveraging a large dataset of design sequences enhances model performance.

Abstract

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.