Can I read Proposal Flow: Semantic Correspondences from Object Proposals on EtoBox?

Proposal Flow: Semantic Correspondences from Object Proposals by Ham, Bumsub; Cho, Minsu; Schmid, Cordelia; Ponce, Jean is a scholarly article available to read on EtoBox.

What is Proposal Flow: Semantic Correspondences from Object Proposals about?

Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handle images depicting different instances of the same object or scene category. We introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals. Unlike prevailing semantic flow approaches that operate on pixels or regularly sampled local regions, proposal flow benefits from the characteristics of modern object proposals, that exhibit high repeatability at multiple scales, and can take advantage of both local and geometric consistency constraints among proposals. We also show that the corresponding sparse proposal flow can effectively be transformed into a conventional dense flow field. We introduce two new challenging datasets that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use these benchmarks to compare different matching algorithms, object proposals, and region features within proposal flow, to the state of the art in semantic flow. This comparison, along with exp

Author

Ham, Bumsub; Cho, Minsu; Schmid, Cordelia; Ponce, Jean

Published

2017

Language

EN