Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917364104167424 |
|---|---|
| author | Artru, Noé Hussain, Rukhshanda Got, Emeline Messier, Alexandre Lindell, David B. Dib, Abdallah |
| author_facet | Artru, Noé Hussain, Rukhshanda Got, Emeline Messier, Alexandre Lindell, David B. Dib, Abdallah |
| contents | Reconstructing high-fidelity 3D head geometry from images is critical for a wide range of applications, yet existing methods face fundamental limitations. Traditional photogrammetry achieves exceptional detail but requires extensive camera arrays (25-200+ views), substantial computation, and manual cleanup in challenging areas like facial hair. Recent alternatives present a fundamental trade-off: foundation models enable efficient single-image reconstruction but lack fine geometric detail, while optimization-based methods achieve higher fidelity but require dense views and expensive computation. We bridge this gap with a hybrid approach that combines the strengths of both paradigms. Our method introduces a multi-view surface normal prediction model that extends monocular foundation models with cross-view attention to produce geometrically consistent normals in a feed-forward pass. We then leverage these predictions as strong geometric priors within an inverse rendering optimization framework to recover high-frequency surface details. Our approach outperforms state-of-the-art single-image and multi-view methods, achieving high-fidelity reconstruction on par with dense-view photogrammetry while reducing camera requirements and computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21100 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction Artru, Noé Hussain, Rukhshanda Got, Emeline Messier, Alexandre Lindell, David B. Dib, Abdallah Computer Vision and Pattern Recognition Graphics 68U05 (Primary) 68T45 (Secondary) I.2.10; I.3.5; I.4.5; I.5.1; I.5.4 Reconstructing high-fidelity 3D head geometry from images is critical for a wide range of applications, yet existing methods face fundamental limitations. Traditional photogrammetry achieves exceptional detail but requires extensive camera arrays (25-200+ views), substantial computation, and manual cleanup in challenging areas like facial hair. Recent alternatives present a fundamental trade-off: foundation models enable efficient single-image reconstruction but lack fine geometric detail, while optimization-based methods achieve higher fidelity but require dense views and expensive computation. We bridge this gap with a hybrid approach that combines the strengths of both paradigms. Our method introduces a multi-view surface normal prediction model that extends monocular foundation models with cross-view attention to produce geometrically consistent normals in a feed-forward pass. We then leverage these predictions as strong geometric priors within an inverse rendering optimization framework to recover high-frequency surface details. Our approach outperforms state-of-the-art single-image and multi-view methods, achieving high-fidelity reconstruction on par with dense-view photogrammetry while reducing camera requirements and computational cost. |
| title | Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction |
| topic | Computer Vision and Pattern Recognition Graphics 68U05 (Primary) 68T45 (Secondary) I.2.10; I.3.5; I.4.5; I.5.1; I.5.4 |
| url | https://arxiv.org/abs/2602.21100 |