Proposal Flow

TL;DR

Proposal flow is a novel semantic flow method that uses object proposals for reliable image correspondence, outperforming existing methods and adaptable to dense flow fields, with a new dataset for evaluation.

Contribution

Introduces proposal flow, a new semantic flow approach leveraging object proposals, and provides a new dataset for benchmarking semantic flow methods.

Findings

Proposal flow outperforms existing semantic flow methods.

Object proposals exhibit high repeatability at multiple scales.

Proposal flow can be transformed into dense flow fields.

Abstract

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 proposal flow can effectively be transformed into a conventional dense flow field. We introduce a new dataset that can be used to evaluate both general semantic flow techniques and region-based approaches such as proposal flow. We use this benchmark 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 experiments on standard datasets, demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.