Journal
ACM TRANSACTIONS ON GRAPHICS
Volume 30, Issue 6, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/2024156.2024159
Keywords
shape segmentation; shape correspondence; linear programming
Categories
Funding
- NSF [0808515, 1011228]
- Stanford-KAUST AEA
- Stanford Graduate Fellowship
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [1011228] Funding Source: National Science Foundation
- Division Of Mathematical Sciences
- Direct For Mathematical & Physical Scien [808515] Funding Source: National Science Foundation
Ask authors/readers for more resources
We present an approach to segmenting shapes in a heterogenous shape database. Our approach segments the shapes jointly, utilizing features from multiple shapes to improve the segmentation of each. The approach is entirely unsupervised and is based on an integer quadratic programming formulation of the joint segmentation problem. The program optimizes over possible segmentations of individual shapes as well as over possible correspondences between segments from multiple shapes. The integer quadratic program is solved via a linear programming relaxation, using a block coordinate descent procedure that makes the optimization feasible for large databases. We evaluate the presented approach on the Princeton segmentation benchmark and show that joint shape segmentation significantly outperforms single-shape segmentation techniques.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available