Metraipolis › archive › dc_fae007437d73

MatLoom: Layered Text-to-Material Generation in a Compact Program Space — arXiv:2609.40322

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40322
License (as archived)
CC0-1.0
Archived
2026-10-07T12:46:22.335Z
SHA-256 of the archived text
6b95713b3978860827d2da80e2fa033a61e22b7ba557e2a55632d665f71b4dfd
Stable URL of this page
https://metraipolis.com/documento/dc_fae007437d73

How to cite

MatLoom: Layered Text-to-Material Generation in a Compact Program Space — arXiv:2609.40322 — arXiv (en), https://arxiv.org/abs/2609.40322 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fae007437d73 (Metraipolis archive dc_fae007437d73, sha256 6b95713b3978860827d2da80e2fa033a61e22b7ba557e2a55632d665f71b4dfd)
BibTeX
@misc{dcfae007437d73,
  title = {MatLoom: Layered Text-to-Material Generation in a Compact Program Space — arXiv:2609.40322},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40322},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fae007437d73; sha256 6b95713b3978860827d2da80e2fa033a61e22b7ba557e2a55632d665f71b4dfd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40322. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented language for text-to-material generation with pretrained language models. Each program composes alpha-masked layers whose shared spatial expressions define coverage and physically based rendering (PBR) channels, making dependencies between patterns, color, and relief explicit. A standalone interpreter evaluates the program into material maps, while the source retains named fields and layer parameters for subsequent authoring. Without task-specific fine-tuning, our pipeline uses parser-guided repair and preview-based critique to revise material designs, then searches noise seeds while keeping each candidate's remaining source fixed. On a curated benchmark of 141 prompts evaluated with six backbones, our best-performing configuration achieves higher mean scores than three diffusion baselines on all four flat-layout prompt-alignment metrics. Its initial programs already exceed all three baselines on mean BLIPScore, before critique or seed search. Retained programs have a median length of 21 lines when pooled across backbones. In a blind four-way comparison involving 30 participants and 20 prompts, our renders receive 59.2% of choices, compared with 19.3% for the most-preferred baseline. Compact executable programs thus offer a way to generate prompt-aligned materials while retaining their construction as part of the asset.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2609.40322 — 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 2026-10-07T12:14:14.254Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).