Fa\c{c}AID: A Transformer Model for Neuro-Symbolic Facade Reconstruction

TL;DR

This paper presents a transformer-based neuro-symbolic model that converts segmented facade images into procedural definitions, enabling flexible and editable architectural facade design through learned transformations.

Contribution

It introduces a novel split grammar for facades, creates a dataset of facades with procedural representations, and trains a transformer model for facade-to-procedural conversion.

Findings

Successful conversion of facade segments into procedural grammar

Enhanced design flexibility through editable procedural representations

Automated transformation process for facade reconstruction

Abstract

We introduce a neuro-symbolic transformer-based model that converts flat, segmented facade structures into procedural definitions using a custom-designed split grammar. To facilitate this, we first develop a semi-complex split grammar tailored for architectural facades and then generate a dataset comprising of facades alongside their corresponding procedural representations. This dataset is used to train our transformer model to convert segmented, flat facades into the procedural language of our grammar. During inference, the model applies this learned transformation to new facade segmentations, providing a procedural representation that users can adjust to generate varied facade designs. This method not only automates the conversion of static facade images into dynamic, editable procedural formats but also enhances the design flexibility, allowing for easy modifications.