Metraipolis › archive › dc_e09e27f7559d

Joint Rigid Alignment and Morphable Reconstruction from Partial 3D Face Scans — arXiv:2610.39161

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39161
License (as archived)
CC0-1.0
Archived
2026-11-01T02:41:49.787Z
SHA-256 of the archived text
87c25da6be6cc8567bbeddd5144a9776308d754a987fce43d848bf4067839835
Stable URL of this page
https://metraipolis.com/documento/dc_e09e27f7559d

How to cite

Joint Rigid Alignment and Morphable Reconstruction from Partial 3D Face Scans — arXiv:2610.39161 — arXiv (en), https://arxiv.org/abs/2610.39161 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e09e27f7559d (Metraipolis archive dc_e09e27f7559d, sha256 87c25da6be6cc8567bbeddd5144a9776308d754a987fce43d848bf4067839835)
BibTeX
@misc{dce09e27f7559d,
  title = {Joint Rigid Alignment and Morphable Reconstruction from Partial 3D Face Scans — arXiv:2610.39161},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39161},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e09e27f7559d; sha256 87c25da6be6cc8567bbeddd5144a9776308d754a987fce43d848bf4067839835},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39161. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Aligning a partial, real-world 3D face scan to a canonical representation requires solving two coupled problems at once: estimating the rigid pose that brings the scan into a common frame, and completing the facial shape in regions the scan never observed. Existing pipelines typically decouple these steps, running a generic point-cloud registration front end followed by a separate non-rigid fitting or deformation stage. Building on the GeoTransformer superpoint-matching architecture, we propose a single network that predicts both a rigid pose and a shape-complete point cloud in one forward pass: a cross-attention regressor, conditioned on transformer point features and predicted coarse correspondences, maps a partial scan to per-patch coefficients of a 3D morphable face model learned offline from a corpus of 8,000 identities. The resulting morphed template is then used, in the same forward pass, as the target for fine-grained Sinkhorn matching and rigid pose estimation, supervised purely by geometric alignment to ground-truth morphed geometry, so no hand-labeled coefficients are required. Against six classical and learned non-rigid registration baselines on held-out identities, our method leads the strongest ones by 3-4 times on per-vertex error and baselines that collapse the head onto the visible region by more than an order of magnitude, and is simultaneously the most accurate and fastest method on ground-truth-free scans from two independent real-scan datasets, NoW and NPHM. Code will be made publicly available.

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/2610.39161 — 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 2026-11-01T02:16:43.911Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).