Image-driven unsupervised 3D model co-segmentation

Liu, Juncheng, Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884, Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766, Xiao, Jianguo and Lian, Zhouhui 2019. Image-driven unsupervised 3D model co-segmentation. Visual Computer 35 (6-8) , pp. 909-920. 10.1007/s00371-019-01679-6

Preview

PDF - Accepted Post-Print Version Download (36MB) | Preview

Abstract

Segmentation of 3D models is a fundamental task in computer graphics and vision. Geometric methods usually lead to non-semantic and fragmentary segmentations. Learning techniques require a large amount of labeled training data. In this paper, we explore the feasibility of 3D model segmentation by taking advantage of the huge number of easy-to-obtain 2D realistic images available on the Internet. The regional color exhibited in images provides information that is valuable for segmentation. To transfer the segmentations, we first filter out inappropriate images with several criteria. The views of these images are estimated by our proposed texture-invariant view estimation Siamese network. The training samples are generated by rendering-based synthesis without laborious labeling. Subsequently, we transfer and merge the segmentations produced by each individual image by applying registration and a graph-based aggregation strategy. The final result is obtained by combining all segmentations within the 3D model set. Our qualitative and quantitative experimental results on several model categories validate effectiveness of our proposed method.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Springer Verlag
ISSN:	0178-2789
Date of First Compliant Deposit:	23 May 2019
Date of Acceptance:	24 April 2019
Last Modified:	16 Nov 2024 09:45
URI:	https://orca.cardiff.ac.uk/id/eprint/122810

Citation Data

Cited 5 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item