Abstract | ||
---|---|---|
This paper presents a data-driven approach to simultaneous segmentation and labeling of parts in 3D meshes. An objective function is formulated as a Conditional Random Field model, with terms assessing the consistency of faces with labels, and terms between labels of neighboring faces. The objective function is learned from a collection of labeled training meshes. The algorithm uses hundreds of geometric and contextual label features and learns different types of segmentations for different tasks, without requiring manual parameter tuning. Our algorithm achieves a significant improvement in results over the state-of-the-art when evaluated on the Princeton Segmentation Benchmark, often producing segmentations and labelings comparable to those produced by humans. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1833349.1778839 | ACM Trans. Graph. |
Keywords | Field | DocType |
medial axis,shape analysis,objective function,conditional random field,stability | Conditional random field,Computer vision,Scale-space segmentation,Polygon mesh,Computer science,Segmentation,Medial axis,Artificial intelligence,Shape analysis (digital geometry) | Journal |
Volume | Issue | ISSN |
29 | 4 | 0730-0301 |
Citations | PageRank | References |
210 | 6.61 | 45 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Evangelos Kalogerakis | 1 | 1377 | 53.82 |
Aaron Hertzmann | 2 | 6002 | 352.67 |
Karan Singh | 3 | 1529 | 76.00 |