Metraipolis › archive › dc_ba6b281ca64e

DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model — arXiv:2609.35242

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35242
License (as archived): CC0-1.0
Archived: 2026-10-07T23:52:42.293Z
SHA-256 of the archived text: cbef2fb998c17e245d8f8639a5d67493abcc19dffaaaa3f294375a3591532c27
Stable URL of this page: https://metraipolis.com/documento/dc_ba6b281ca64e

How to cite

DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model — arXiv:2609.35242 — arXiv (en), https://arxiv.org/abs/2609.35242 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba6b281ca64e (Metraipolis archive dc_ba6b281ca64e, sha256 cbef2fb998c17e245d8f8639a5d67493abcc19dffaaaa3f294375a3591532c27)

BibTeX

@misc{dcba6b281ca64e,
  title = {DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model — arXiv:2609.35242},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35242},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba6b281ca64e; sha256 cbef2fb998c17e245d8f8639a5d67493abcc19dffaaaa3f294375a3591532c27},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35242. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scalable Vector Graphics (SVG) are essential for modern industrial Computer-Aided Design (CAD). However, existing autoregressive SVG generation models are predominantly tailored for artistic creation and struggle to maintain the rigorous geometric fidelity and cross-view spatial alignment required for engineering drawings. To bridge this gap, we introduce \textbf{DrawingsDreamer}, a unified Large Language Model (LLM)-driven framework for multi-view vector-based engineering drawings generation. By formulating the generation of multi-view engineering drawings purely as a sequence modeling task, we eliminate the need of raster image encoders. We propose a Streamlined Representation utilizing hierarchical postfix tokenization, which guides the model to establish local geometric coordinates before assigning semantic boundaries. Optimized via a progressive task-aware curriculum schedule, \textbf{DrawingsDreamer} effectively transitions from localized structural repair to macroscopic generation in a unified model. Extensive experiments demonstrate that our unified model achieves strong performance in both geometric fidelity and syntactic accuracy across diverse conditional and unconditional generation tasks.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35242 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T23:29:27.537Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).