Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation

dc.contributor.author	Fu, Changqing
dc.contributor.author	Cohen, Laurent D.
dc.date.accessioned	2022-02-15T10:01:44Z
dc.date.available	2022-02-15T10:01:44Z
dc.date.issued	2021
dc.identifier.uri	https://basepub.dauphine.psl.eu/handle/123456789/22616
dc.language.iso	en	en
dc.subject	Machine Learning
dc.subject	Image Generation
dc.subject	Generative Adversarial Network
dc.subject	Image deformation
dc.subject	Contour Editing
dc.subject.ddc	621.3	en
dc.title	Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation
dc.type	Communication / Conférence
dc.description.abstracten	A novel two-stage approach is proposed for image manipulation and generation. User-interactive image deformation is performed through editing of contours. This is performed in the latent edge space with both color and gradient information. The output of editing is then fed into a multi-scale representation of the image to recover quality output. The model is flexible in terms of transferability and training efficiency.
dc.subject.ddclabel	Traitement du signal	en
dc.relation.conftitle	Eighth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)
dc.relation.confdate	2021-05
dc.relation.confcity	on line
dc.relation.confcountry	FRANCE
dc.relation.forthcoming	non	en
dc.description.ssrncandidate	non
dc.description.halcandidate	non
dc.description.readership	recherche
dc.description.audience	International
dc.date.updated	2022-11-21T15:45:22Z

Related items