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...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/105015 http://hdl.handle.net/10220/16822 |
| _version_ | 1826116017445666816 |
|---|---|
| author | Meng, Min Xia, Jiazhi Luo, Jun He, Ying |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Meng, Min Xia, Jiazhi Luo, Jun He, Ying |
| author_sort | Meng, Min |
| collection | NTU |
| description | 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. |
| first_indexed | 2024-10-01T04:04:33Z |
| format | Journal Article |
| id | ntu-10356/105015 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:04:33Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/1050152020-05-28T07:41:40Z Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization Meng, Min Xia, Jiazhi Luo, Jun He, Ying School of Computer Engineering DRNTU::Engineering::Computer science and engineering 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. 2013-10-24T08:10:40Z 2019-12-06T21:44:31Z 2013-10-24T08:10:40Z 2019-12-06T21:44:31Z 2012 2012 Journal Article Meng, M., Xia, J., Luo, J., & He, Y. (2013). Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization. Computer-Aided Design, 45(2), 312-320. 0010-4485 https://hdl.handle.net/10356/105015 http://hdl.handle.net/10220/16822 10.1016/j.cad.2012.10.014 en Computer-aided design |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Meng, Min Xia, Jiazhi Luo, Jun He, Ying Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization |
| title | Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization |
| title_full | Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization |
| title_fullStr | Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization |
| title_full_unstemmed | Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization |
| title_short | Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization |
| title_sort | unsupervised co segmentation for 3d shapes using iterative multi label optimization |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/105015 http://hdl.handle.net/10220/16822 |
| work_keys_str_mv | AT mengmin unsupervisedcosegmentationfor3dshapesusingiterativemultilabeloptimization AT xiajiazhi unsupervisedcosegmentationfor3dshapesusingiterativemultilabeloptimization AT luojun unsupervisedcosegmentationfor3dshapesusingiterativemultilabeloptimization AT heying unsupervisedcosegmentationfor3dshapesusingiterativemultilabeloptimization |