RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction - Calcul Intensif, Simulation, Optimisation
Conference Papers Year : 2024

RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction

Abstract

This paper introduces a versatile paradigm for integrating multi-view reflectance (optional) and normal maps acquired through photometric stereo. Our approach employs a pixel-wise joint re-parameterization of reflectance and normal, considering them as a vector of radiances rendered under simulated, varying illumination. This reparameterization enables the seamless integration of reflectance and normal maps as input data in neural volume rendering-based 3D reconstruction while preserving a single optimization objective. In contrast, recent multi-view photometric stereo (MVPS) methods depend on multiple, potentially conflicting objectives. Despite its apparent simplicity, our proposed approach outperforms state-of-the-art approaches in MVPS benchmarks across F-score, Chamfer distance, and mean angular error metrics. Notably, it significantly improves the detailed 3D reconstruction of areas with high curvature or low visibility.
Fichier principal
Vignette du fichier
Reflectance_and_normals_aware_3D_reconstruction___preprint (1).pdf (24.15 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04526751 , version 1 (29-03-2024)
hal-04526751 , version 2 (02-04-2024)

Identifiers

  • HAL Id : hal-04526751 , version 2

Cite

Baptiste Brument, Robin Bruneau, Yvain Quéau, Jean Mélou, François Lauze, et al.. RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction. IEEE / CVF International Conference on Computer Vision and Pattern Recognition (CVPR 2024), IEEE, Jun 2024, Seattle, United States. pp.5230-5239. ⟨hal-04526751v2⟩
861 View
19 Download

Share

More