Medial Spectral Coordinates for 3D Shape Analysis

In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes, their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applicatio...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 2676 - 2686
Hlavní autoři: Rezanejad, Morteza, Khodadad, Mohammad, Mahyar, Hamidreza, Lombaert, Herve, Gruninger, Michael, Walther, Dirk, Siddiqi, Kaleem
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
categorization
Computational modeling
Computer vision
Deep learning
grouping and shape analysis; Recognition: detection
Point cloud compression
retrieval; Representation learning
Segmentation
Shape
Solid modeling
Three-dimensional displays
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes, their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral co-ordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to iso-metric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00271