Metraipolis › archive › dc_32622cdc473b

Texture Space Material Diffusion — arXiv:2609.37654

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37654
License (as archived)
CC0-1.0
Archived
2026-10-07T18:41:25.838Z
SHA-256 of the archived text
848c50ed4b1e9e0716419f9428d29528cf53b394703b07ad048e7a5701be90a2
Stable URL of this page
https://metraipolis.com/documento/dc_32622cdc473b

How to cite

Texture Space Material Diffusion — arXiv:2609.37654 — arXiv (en), https://arxiv.org/abs/2609.37654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_32622cdc473b (Metraipolis archive dc_32622cdc473b, sha256 848c50ed4b1e9e0716419f9428d29528cf53b394703b07ad048e7a5701be90a2)
BibTeX
@misc{dc32622cdc473b,
  title = {Texture Space Material Diffusion — arXiv:2609.37654},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37654},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_32622cdc473b; sha256 848c50ed4b1e9e0716419f9428d29528cf53b394703b07ad048e7a5701be90a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a method for generating high quality materials for 3D objects entirely in texture space. We finetune a video diffusion transformer for text-guided material generation, multi-view material generation, and material upscaling. Our key insight is to use the known projection from image space to texture space, enabling the diffusion process to generalize across arbitrary geometries and texture parameterizations. This approach also avoids the view consistency issues inherent in video and multi-view diffusion models. Because texture space is two dimensional, we can reuse the strong priors of pretrained video diffusion models. We apply our method to high quality material reconstruction from posed photos captured under unknown lighting, as well as to text- and image guided material generation. Our method can scale to high resolutions (8K), 100+ input views, and neural material representations. In quantitative and qualitative evaluations we show state-of-the-art results for material generation and reconstruction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.37654 — 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 2026-10-07T18:04:24.894Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).