A Survey of Simple Geometric Primitives Detection Methods for Captured 3D Data

Abstract

The amount of captured 3D data is continuously increasing, with the democratization of consumer depth cameras, the development of modern multi‐view stereo capture setups and the rise of single‐view 3D capture based on machine learning. The analysis and representation of this ever growing volume of 3D data, often corrupted with acquisition noise and reconstruction artefacts, is a serious challenge at the frontier between computer graphics and computer vision. To that end, segmentation and optimization are crucial analysis components of the shape abstraction process, which can themselves be greatly simplified when performed on lightened geometric formats. In this survey, we review the algorithms which extract simple geometric primitives from raw dense 3D data. After giving an introduction to these techniques, from the acquisition modality to the underlying theoretical concepts, we propose an application‐oriented characterization, designed to help select an appropriate method based on one's application needs and compare recent approaches. We conclude by giving hints for how to evaluate these methods and a set of research challenges to be explored.

Supervised Fitting of Geometric Primitives to 3D Point Clouds

“…Among a large body of previous work on fitting primitives to 3D data, we review only methods that fit primitives to objects instead of scenes, as our target use cases are scanned point clouds of individual mechanical parts. For a more comprehensive review, see survey [13].…”

From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

“…We briefly review the literature concerned with extraction of 3D planar structures. For further details and references, we point the reader to a recent, extensive review on the general primitive detection from 3D data [8].…”

“…Furthermore, in the case that the graph G contains vertex groups of a specific structure, we can in addition to orthogonality deduce which planes are parallel [21], which is also not being taking into account in Eq. (8). We address the two constraint types (orthogonal and parallel) differently: first, we re-structure our graph G by combining parallel planes into one node, where each node is endowed with a list of distances {d kl }.…”

3D Shape Segmentation with Geometric Deep Learning

“…triangular meshes, quad meshes, CAD models) by decomposing the input shape into several components. Shape decomposition can be performed by clustering shape vertices [8], by using geometrical primitives [9], or by generating range scans from different viewpoints [10]. We use a similar approach to the latter in order to process the 3D shape regardless its 3D representation, resolution and vertex topology.…”