Metraipolis › archive › dc_73d8782ce02c
VISAGE: Vertex-based Intrinsic Surface Appearance GEneration via Dual-Stream Diffusion for Arbitrary 3D Heads — arXiv:2611.04712
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04712
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:03:25.538Z
- SHA-256 of the archived text
d762efeb0089b0ecc18175657911ceb951e614e1113d0fb95f72c99f85c48fea- Stable URL of this page
https://metraipolis.com/documento/dc_73d8782ce02c
How to cite
VISAGE: Vertex-based Intrinsic Surface Appearance GEneration via Dual-Stream Diffusion for Arbitrary 3D Heads — arXiv:2611.04712 — arXiv (en), https://arxiv.org/abs/2611.04712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73d8782ce02c (Metraipolis archive dc_73d8782ce02c, sha256 d762efeb0089b0ecc18175657911ceb951e614e1113d0fb95f72c99f85c48fea)
BibTeX
@misc{dc73d8782ce02c,
title = {VISAGE: Vertex-based Intrinsic Surface Appearance GEneration via Dual-Stream Diffusion for Arbitrary 3D Heads — arXiv:2611.04712},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04712},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73d8782ce02c; sha256 d762efeb0089b0ecc18175657911ceb951e614e1113d0fb95f72c99f85c48fea},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recovering identity-faithful, physically based surface appearance for 3D human heads from sparse images remains challenging. Existing methods often rely on UV-based pipelines, introducing seam artefacts, or operate in image space, limiting surface consistency. We present VISAGE, Vertex-based Intrinsic Surface Appearance GEneration, a surface-based conditional diffusion framework that synthesises per-vertex albedo and roughness directly on arbitrary mesh topologies, without requiring consistent UV parameterisation at training time. VISAGE combines global spectral processing with local geodesic K-Nearest-Neighbour refinement, enforcing structural coherence while restoring detail beyond the truncated spectral basis. Multi-view RGB images condition the network via visibility-aware cross-attention, enabling occlusion-robust synthesis across the full head surface. Region-specific modules specialise in semantically demanding and distinct areas (eyes, mouth, skin and hair), while a tangent-space output projection recovers fine iris detail. We further introduce a scalable procedural augmentation pipeline that enriches raw geometry scans with physically plausible albedo, roughness and normal maps for training. The predicted attributes render directly as a single RGBA vertex-colour channel. VISAGE reduces FID by 42.7% on NPHM and 22.5% and 4.4% on zero-shot FaceVerse and i3DMM, respectively, relative to the strongest baseline, with a 7.2M-parameter core network. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.04712 — 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 2026-11-04T18:39:37.533Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).