FaçAID: A Transformer Model for Neuro-Symbolic Facade Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916392430731264 |
|---|---|
| author | Plocharski, Aleksander Swidzinski, Jan Porter-Sobieraj, Joanna Musialski, Przemyslaw |
| author_facet | Plocharski, Aleksander Swidzinski, Jan Porter-Sobieraj, Joanna Musialski, Przemyslaw |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01829 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FaçAID: A Transformer Model for Neuro-Symbolic Facade Reconstruction Plocharski, Aleksander Swidzinski, Jan Porter-Sobieraj, Joanna Musialski, Przemyslaw Graphics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing I.3.5; I.2.2; I.4.5 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. |
| title | FaçAID: A Transformer Model for Neuro-Symbolic Facade Reconstruction |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing I.3.5; I.2.2; I.4.5 |
| url | https://arxiv.org/abs/2406.01829 |