FaçAID: A Transformer Model for Neuro-Symbolic Facade Reconstruction
This work addresses a domain-specific problem in architectural design by enabling dynamic modifications of facades, but it is incremental as it builds on existing transformer and neuro-symbolic approaches.
The paper tackles the problem of converting static facade images into editable procedural formats by introducing a neuro-symbolic transformer model that automates this conversion, enhancing design flexibility for users.
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.