Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization

This paper presents an unsupervised algorithm for co-segmentation of a set of 3D shapes of the same family. Taking the over-segmentation results as input, our approach clusters the primitive patches to generate an initial guess. Then, it iteratively builds a statistical model to describe each cluste...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computer aided design Ročník 45; číslo 2; s. 312 - 320
Hlavní autori: Meng, Min, Xia, Jiazhi, Luo, Jun, He, Ying
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.02.2013
Predmet:
Algorithms
Benchmarking
Clusters
Co-segmentation
Computer aided design
Construction
Mathematical models
Multi-label optimization
Optimization
Shape correspondence
Three dimensional
Unsupervised algorithm
Co-segmentation
Unsupervised algorithm
Multi-label optimization
Shape correspondence
ISSN:0010-4485, 1879-2685
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper presents an unsupervised algorithm for co-segmentation of a set of 3D shapes of the same family. Taking the over-segmentation results as input, our approach clusters the primitive patches to generate an initial guess. Then, it iteratively builds a statistical model to describe each cluster of parts from the previous estimation, and employs the multi-label optimization to improve the co-segmentation results. In contrast to the existing “one-shot” algorithms, our method is superior in that it can improve the co-segmentation results automatically. The experimental results on the Princeton Segmentation Benchmark demonstrate that our approach is able to co-segment 3D shapes with significant variability and achieves comparable performance to the existing supervised algorithms and better performance than the unsupervised ones. [Display omitted]
Bibliografia:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0010-4485
1879-2685
DOI:10.1016/j.cad.2012.10.014