{ "id": "2312.01215", "version": "v1", "published": "2023-12-02T19:49:27.000Z", "updated": "2023-12-02T19:49:27.000Z", "title": "RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction", "authors": [ "Baptiste Brument", "Robin Bruneau", "Yvain Quéau", "Jean Mélou", "François Bernard Lauze", "Jean-Denis", "Jean-Denis Durou", "Lilian Calvet" ], "comment": "14 pages, 12 figures, 6 tables. The source code will be available at https://github.com/bbrument/RNb-NeuS", "categories": [ "cs.CV" ], "abstract": "This paper introduces a versatile paradigm for integrating multi-view reflectance 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 re-parameterization 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.", "revisions": [ { "version": "v1", "updated": "2023-12-02T19:49:27.000Z" } ], "analyses": { "keywords": [ "normal-based multi-view 3d reconstruction", "reflectance", "mean angular error metrics", "approach outperforms state-of-the-art approaches", "neural volume rendering-based 3d reconstruction" ], "tags": [ "github project" ], "note": { "typesetting": "TeX", "pages": 14, "language": "en", "license": "arXiv", "status": "editable" } } }