Discontinuity-aware Normal Integration for Generic Central Camera Models

TL;DR

This paper introduces a novel normal integration method that explicitly models discontinuities and supports generic central camera models, improving accuracy in 3D surface reconstruction from normal maps.

Contribution

It presents a new formulation that explicitly handles discontinuities and extends normal integration to generic central cameras, unlike previous methods.

Findings

Achieves state-of-the-art results on standard benchmarks.

More accurately models the relation between depth and surface normals.

First method to directly handle generic central camera models.

Abstract

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.