Metraipolis › archive › dc_85b2e2744f4f
GLOSS: Geometric Local Self-Similarity Learning for Faithful Reference-Guided Texture Fill — arXiv:2608.25461
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.25461
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T11:00:11.425Z
- SHA-256 of the archived text
fdd7c375952fb189773476de8a612ca73153a6be202ae9ca469f219917108dde- Stable URL of this page
https://metraipolis.com/documento/dc_85b2e2744f4f
How to cite
GLOSS: Geometric Local Self-Similarity Learning for Faithful Reference-Guided Texture Fill — arXiv:2608.25461 — arXiv (en), https://arxiv.org/abs/2608.25461 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85b2e2744f4f (Metraipolis archive dc_85b2e2744f4f, sha256 fdd7c375952fb189773476de8a612ca73153a6be202ae9ca469f219917108dde)
BibTeX
@misc{dc85b2e2744f4f,
title = {GLOSS: Geometric Local Self-Similarity Learning for Faithful Reference-Guided Texture Fill — arXiv:2608.25461},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.25461},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85b2e2744f4f; sha256 fdd7c375952fb189773476de8a612ca73153a6be202ae9ca469f219917108dde},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.25461. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Using conditional image generators, texture artists can explore many single-view looks for an existing 3D shape. Despite impressive progress, state-of-the-art generative methods still struggle to generate a full object texture while closely adhering to fine scale geometric detail and single view references, leaving little room for artists guidance. Furthermore, current automatic models lack the flexibility for artist to explore multiple textures from varied sources in an interactive and controllable manner. Unlike methods trained on large 3D datasets that generate full object textures from global guidance, our work explores a local and less data-hungry approach to texture with explicit artist control. We leverage the geometric self-similarity and geometry-texture correlation existing in many natural and man-made shapes; and train a shape-specific local texture generation and completion model. This model learns from existing image model priors and a single 3D shape, and is guided by attending to a set of geometry-aware reference patches. The trained shape-specific network can transfer any novel reference to the full target object texture through patchwise inpainting. We show improved or comparable quality to strong image-conditioned texture generation baselines, suggesting local texturing as a promising research direction. Our model also enables local geometry-conditioned texture inpainting, guided by artist-selected references, and generalizes to PBR materials and unseen meshes for texture transfer. We piloted our novel texture fill capability as a Blender addon with several 3D texturing professionals who reported positive feedback on the model's controllability, practical usefulness, and creative affordances. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV). Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.25461 — 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 2026-10-16T10:02:34.421Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).