Efficient relaxations for dense CRFs with sparse higher-order potentials
<p>Dense conditional random fields (CRFs) have become a popular framework for modelling several problems in computer vision such as stereo correspondence and multi-class semantic segmentation. By modelling long- range interactions, dense CRFs provide a labelling that captures finer detail than...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Journal article |
| Published: |
Society for Industrial and Applied Mathematics
2019
|