Deep graphical feature learning for the feature matching problem

Simple item page
dc.contributor.authorZhang, Z.
dc.contributor.authorLee, W.S.
dc.contributor.conferenceIEEE International Conference on Computer Vision (ICCV) (27 Oct 2019 - 2 Nov 2019 : Seoul, South Korea)
dc.date.issued2019
dc.description.abstractThe feature matching problem is a fundamental problem in various areas of computer vision including image registration, tracking and motion analysis. Rich local representation is a key part of efficient feature matching methods. However, when the local features are limited to the coordinate of key points, it becomes challenging to extract rich local representations. Traditional approaches use pairwise or higher order handcrafted geometric features to get robust matching; this requires solving NP-hard assignment problems. In this paper, we address this problem by proposing a graph neural network model to transform coordinates of feature points into local features. With our local features, the traditional NP-hard assignment problems are replaced with a simple assignment problem which can be solved efficiently. Promising results on both synthetic and real datasets demonstrate the effectiveness of the proposed method.
dc.description.statementofresponsibilityZhen Zhang, Wee Sun Lee
dc.identifier.citationProceedings / IEEE International Conference on Computer Vision. IEEE International Conference on Computer Vision, 2019, vol.2019-October, pp.5086-5095
dc.identifier.doi10.1109/ICCV.2019.00519
dc.identifier.isbn9781728148038
dc.identifier.issn1550-5499
dc.identifier.issn2380-7504
dc.identifier.orcidZhang, Z. [0000-0003-2805-4396]
dc.identifier.urihttp://hdl.handle.net/2440/127206
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeLos Alamitos, California
dc.relation.granthttp://purl.org/au-research/grants/arc/DP160100703
dc.relation.ispartofseriesIEEE International Conference on Computer Vision
dc.rights©2019 IEEE
dc.source.urihttps://doi.org/10.1109/iccv.2019.00519
dc.titleDeep graphical feature learning for the feature matching problem
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Australian Institute for Machine Learning publications