Publicación:
An Efficient and Rotation Invariant Fourier-Based Metric for Assessing the Quality of Images Created by Generative Models

Vista sencilla de ítem
dc.contributor.authorGamazo,José María
dc.contributor.authorCuadra Troncoso, José Manuel
dc.contributor.authorRincón Zamorano, Mariano
dc.contributor.funderMinisterio de Ciencia e Innovación (España)
dc.coverage.spatialPuerto de la Cruz, Tenerife, Spain
dc.coverage.temporal2022-05-31
dc.date.accessioned2026-02-05T11:57:34Z
dc.date.available2026-02-05T11:57:34Z
dc.date.issued2022-06-24
dc.description.abstractRecent progress in generative image modeling is leading to a new era of high-resolution fakes visually indistinguishable from real life images. However, the development of metrics capable of discerning whether images are synthetic or not runs behind the race of achieving the best generator, thus bringing potential threats. We propose a rotation invariant metric capable of distinguishing real and generated image datasets and we call it CSD (Circular Spectrum Distance) due to its circular nature and its inherent relation to the Fourier Spectrum. Its performance is analysed on a whole brain MRI dataset. CSD has similar behavior to FID during training but requires smaller batch sizes and is faster to compute.en
dc.description.provenanceSubmitted by Carmen Costumero Serrano (ccostumero@pas.uned.es) on 2026-02-05T11:56:46Z workflow start=Step: editstep - action:claimaction No. of bitstreams: 1 Gamazo2022 - An Efficient And Rotation Invari_MARIANO RINCON ZAMOR.pdf: 1578932 bytes, checksum: 4b92ed15319c91129161a291be676bce (MD5)en
dc.description.provenanceStep: editstep - action:editaction Approved for entry into archive by Carmen Costumero Serrano(ccostumero@pas.uned.es) on 2026-02-05T11:57:34Z (GMT)en
dc.description.provenanceMade available in DSpace on 2026-02-05T11:57:34Z (GMT). No. of bitstreams: 1 Gamazo2022 - An Efficient And Rotation Invari_MARIANO RINCON ZAMOR.pdf: 1578932 bytes, checksum: 4b92ed15319c91129161a291be676bce (MD5) Previous issue date: 2022-06-24en
dc.description.versionversión final
dc.identifier.citationGamazo, J., Cuadra, J.M., Rincón, M. (2022). An Efficient and Rotation Invariant Fourier-Based Metric for Assessing the Quality of Images Created by Generative Models. In: Ferrández Vicente, J.M., Álvarez-Sánchez, J.R., de la Paz López, F., Adeli, H. (eds) Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence. IWINAC 2022. Lecture Notes in Computer Science, vol 13259. Springer, Cham. https://doi.org/10.1007/978-3-031-06527-9_41
dc.identifier.doihttps://doi.org/10.1007/978-3-031-06527-9_41
dc.identifier.isbn978-3-031-06526-2
dc.identifier.isbn978-3-031-06527-9
dc.identifier.urihttps://hdl.handle.net/20.500.14468/31720
dc.language.isoen
dc.publisherSpringer
dc.relation.centerE.T.S. de Ingeniería Informática
dc.relation.congress9th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2022, Puerto de la Cruz, Tenerife, Spain, May 31 – June 3, 2022, Proceedings, Part II
dc.relation.departmentInteligencia Artificial
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.subject1203.17 Informática
dc.subject.odsODS 9 - Industria, innovación e infraestructura
dc.titleAn Efficient and Rotation Invariant Fourier-Based Metric for Assessing the Quality of Images Created by Generative Modelsen
dc.typeactas de congresoes
dc.typeconference proceedingsen
dspace.entity.typePublication
relation.isAuthorOfPublicationfa1a8e74-c3ef-42cf-b132-ac98810c1b92
relation.isAuthorOfPublication06a389cc-435e-4713-a8d7-8350f08ea1a8
relation.isAuthorOfPublication.latestForDiscoveryfa1a8e74-c3ef-42cf-b132-ac98810c1b92
Archivos
Bloque original
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
Gamazo2022 - An Efficient And Rotation Invari_MARIANO RINCON ZAMOR.pdf
Tamaño:
1.51 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.62 KB
Formato:
Item-specific license agreed to upon submission
Descripción:
Descargar
Colecciones
Actas y comunicaciones de congresos