Discontinuity-aware Normal Integration for Generic Central Camera Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Milano, Francesco, López-Antequera, Manuel, Dhingra, Naina, Siegwart, Roland, Thiel, Robert
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909762303557632
author Milano, Francesco
López-Antequera, Manuel
Dhingra, Naina
Siegwart, Roland
Thiel, Robert
author_facet Milano, Francesco
López-Antequera, Manuel
Dhingra, Naina
Siegwart, Roland
Thiel, Robert
contents Recovering a 3D surface from its surface normal map, a problem known as normal integration, is a key component for photometric shape reconstruction techniques such as shape-from-shading and photometric stereo. The vast majority of existing approaches for normal integration handle only implicitly the presence of depth discontinuities and are limited to orthographic or ideal pinhole cameras. In this paper, we propose a novel formulation that allows modeling discontinuities explicitly and handling generic central cameras. Our key idea is based on a local planarity assumption, that we model through constraints between surface normals and ray directions. Compared to existing methods, our approach more accurately approximates the relation between depth and surface normals, achieves state-of-the-art results on the standard normal integration benchmark, and is the first to directly handle generic central camera models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06075
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Discontinuity-aware Normal Integration for Generic Central Camera Models
Milano, Francesco
López-Antequera, Manuel
Dhingra, Naina
Siegwart, Roland
Thiel, Robert
Computer Vision and Pattern Recognition
Recovering a 3D surface from its surface normal map, a problem known as normal integration, is a key component for photometric shape reconstruction techniques such as shape-from-shading and photometric stereo. The vast majority of existing approaches for normal integration handle only implicitly the presence of depth discontinuities and are limited to orthographic or ideal pinhole cameras. In this paper, we propose a novel formulation that allows modeling discontinuities explicitly and handling generic central cameras. Our key idea is based on a local planarity assumption, that we model through constraints between surface normals and ray directions. Compared to existing methods, our approach more accurately approximates the relation between depth and surface normals, achieves state-of-the-art results on the standard normal integration benchmark, and is the first to directly handle generic central camera models.
title Discontinuity-aware Normal Integration for Generic Central Camera Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.06075