Article Dans Une Revue International Journal of Computer Vision Année : 2026

Multi-view Surface Reconstruction Using Normal and Reflectance Cues

Résumé

Achieving high-fidelity 3D surface reconstruction while preserving fine details remains challenging, especially in the presence of materials with complex reflectance properties and without a dense-view setup. In this paper, we introduce a versatile framework that incorporates multi-view normal and optionally reflectance maps into radiance-based surface reconstruction. Our approach employs a pixelwise joint re-parametrization of reflectance and surface normals, representing them as a vector of radiances under simulated, varying illumination. This formulation enables seamless incorporation into standard surface reconstruction pipelines, such as traditional multi-view stereo (MVS) frameworks or modern neural volume rendering (NVR) ones. Combined with the latter, our approach achieves state-of-the-art performance on multi-view photometric stereo (MVPS) benchmark datasets, including DiLiGenT-MV, LUCES-MV and Skoltech3D. In particular, our method excels in reconstructing finegrained details and handling challenging visibility conditions. The present paper is an extended version of the earlier conference paper by Brument et al. (in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024), featuring an accelerated and more robust algorithm as well as a broader empirical evaluation. The code and data relative to this article is available at https://github.com/RobinBruneau/RNb-NeuS2.

Fichier sous embargo
Fichier sous embargo
0 2 2
Année Mois Jours
Avant la publication
lundi 13 juillet 2026
Fichier sous embargo
lundi 13 juillet 2026
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-05455975 , version 1 (13-01-2026)

Licence

Identifiants

Citer

Robin Bruneau, Baptiste Brument, Yvain Quéau, Jean Mélou, François Bernard Lauze, et al.. Multi-view Surface Reconstruction Using Normal and Reflectance Cues. International Journal of Computer Vision, 2026, 134 (69), ⟨10.1007/s11263-025-02628-8⟩. ⟨hal-05455975⟩
3275 Consultations
20 Téléchargements

Altmetric

Partager

  • More