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

Autor:	Plocharski, Aleksander, Swidzinski, Jan, Porter-Sobieraj, Joanna, Musialski, Przemyslaw
Rok vydání:	2024
Předmět:	Computer Science - Graphics Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Computer Science - Neural and Evolutionary Computing I.3.5 I.2.2 I.4.5
Druh dokumentu:	Working Paper
Popis:	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. Comment: 11 pages, 11 figures, in ACM SIGGRAPH Asia 2024 Conference Papers Proceedings
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.01829 Zobrazit plný text záznamu View this record from Arxiv