Reverse Browser: Vector-Image-to-Code Generator
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912573957341184 |
|---|---|
| author | Toth-Czifra, Zoltan |
| author_facet | Toth-Czifra, Zoltan |
| contents | Automating the conversion of user interface design into code (image-to-code or image-to-UI) is an active area of software engineering research. However, the state-of-the-art solutions do not achieve high fidelity to the original design, as evidenced by benchmarks. In this work, I approach the problem differently: I use vector images instead of bitmaps as model input. I create several large datasets for training machine learning models. I evaluate the available array of Image Quality Assessment (IQA) algorithms and introduce a new, multi-scale metric. I then train a large open-weights model and discuss its limitations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reverse Browser: Vector-Image-to-Code Generator Toth-Czifra, Zoltan Software Engineering Artificial Intelligence Automating the conversion of user interface design into code (image-to-code or image-to-UI) is an active area of software engineering research. However, the state-of-the-art solutions do not achieve high fidelity to the original design, as evidenced by benchmarks. In this work, I approach the problem differently: I use vector images instead of bitmaps as model input. I create several large datasets for training machine learning models. I evaluate the available array of Image Quality Assessment (IQA) algorithms and introduce a new, multi-scale metric. I then train a large open-weights model and discuss its limitations. |
| title | Reverse Browser: Vector-Image-to-Code Generator |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2509.05394 |