PatchMatchGraph: Building a Graph of Dense Patch Correspondences for Label Transfer

Stephen Gould and Yuhang Zhang

Abstract. We address the problem of semantic segmentation, or multi-class pixel labeling, by constructing a graph of dense overlapping patch correspondences across large image sets. We then transfer annotations from labeled images to unlabeled images using the established patch correspondences. Unlike previous approaches to non-parametric label transfer our approach does not require an initial image retrieval step. Moreover, we operate on a graph for computing mappings between images, which avoids the need for exhaustive pairwise comparisons. Consequently, we can leverage offline computation to enhance performance at test time. We conduct extensive experiments to analyze different variants of our graph construction algorithm and evaluate multi-class pixel labeling performance on several challenging datasets.

LNCS 7576, p. 439 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012