A survey on deep geometry learning: from a representation perspective

Xiao, Yun-Peng, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680, Zhang, Fang-Lue, Li, Chunpeng and Gao, Lin 2020. A survey on deep geometry learning: from a representation perspective. Computational Visual Media 6 (2) , pp. 113-133. 10.1007/s41095-020-0174-8

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Researchers have achieved great success in dealing with 2D images using deep learning. In recent years, 3D computer vision and geometry deep learning have gained ever more attention. Many advanced techniques for 3D shapes have been proposed for different applications. Unlike 2D images, which can be uniformly represented by a regular grid of pixels, 3D shapes have various representations, such as depth images, multi-view images, voxels, point clouds, meshes, implicit surfaces, etc. The performance achieved in different applications largely depends on the representation used, and there is no unique representation that works well for all applications. Therefore, in this survey, we review recent developments in deep learning for 3D geometry from a representation perspective, summarizing the advantages and disadvantages of different representations for different applications. We also present existing datasets in these representations and further discuss future research directions.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Springer
ISSN:	2096-0433
Funders:	Royal Society
Date of First Compliant Deposit:	16 June 2020
Date of Acceptance:	17 April 2020
Last Modified:	05 May 2023 11:25
URI:	https://orca.cardiff.ac.uk/id/eprint/132484

Citation Data

Cited 37 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item