Publications

Detailed Information

Beyond homography: nonparametric image alignment via graph convolutional networks

DC Field Value Language
dc.contributor.authorKim, Mijeong-
dc.contributor.authorChu, Sanghyeok-
dc.contributor.authorHan, Bohyung-
dc.date.accessioned2022-10-07T06:19:31Z-
dc.date.available2022-10-07T06:19:31Z-
dc.date.created2022-09-27-
dc.date.issued2022-11-
dc.identifier.citationMachine Vision and Applications, Vol.33 No.6, p. 89-
dc.identifier.issn0932-8092-
dc.identifier.urihttps://hdl.handle.net/10371/185619-
dc.description.abstractWe propose an image alignment algorithm based on weak supervision, which aims to identify the correspondence between a pair of reference and target images with no supervision of individual pixels. Since most existing methods have relied on a predefined geometric model such as homography, they often suffer from a lack of model flexibility and generalizability. To tackle the challenge, we propose a novel nonparametric transformation model based on graph convolutional networks without an explicit geometric constraint. The proposed method is generic and flexible in the sense that it is applicable to the image pairs undergoing diverse local and/or global transformations. To make the algorithm more suitable for real-world scenarios having potential noises from moving objects, we disregard those objects with an off-the-shelf semantic segmentation model. The proposed algorithm is evaluated on the Cityscapes dataset with annotated pixel-level correspondences and outperforms baseline methods relying on global parametric transformations.-
dc.language영어-
dc.publisherSpringer Verlag-
dc.titleBeyond homography: nonparametric image alignment via graph convolutional networks-
dc.typeArticle-
dc.identifier.doi10.1007/s00138-022-01331-9-
dc.citation.journaltitleMachine Vision and Applications-
dc.identifier.wosid000855459100001-
dc.citation.number6-
dc.citation.startpage89-
dc.citation.volume33-
dc.description.isOpenAccessN-
dc.contributor.affiliatedAuthorHan, Bohyung-
dc.type.docTypeArticle-
dc.description.journalClass1-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share