Publication
Dual critic conditional wasserstein gAN for height-map generation
dc.contributor.author | Ramos, Nuno | |
dc.contributor.author | Santos, Pedro | |
dc.contributor.author | Dias, João | |
dc.date.accessioned | 2023-12-15T11:07:33Z | |
dc.date.available | 2023-12-15T11:07:33Z | |
dc.date.issued | 2023 | |
dc.description.abstract | Traditionally, video-game maps are either made by hand, requiring many man-hours to produce good results, or made using Procedural Content Generation (PCG) techniques, which rely on a predetermined algorithm to generate every feature of the map. More recent studies have tried an approach using Deep Learning algorithms, which have their own limitations, in particular taking away the creative freedom of the designers. To circumvent this problem we propose a system that transforms low fidelity sketches into realistic height-maps through a Deep Learning model we call the Dual Critic Conditional Wasserstein GAN (DCCWGAN), thus providing high visual quality without removing control from the user. The presented system is capable of producing images that resemble the received input, and a user study with 79 participants showed that observers are not able to distinguish between earth-based height-map images and the images generated by our system. | pt_PT |
dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
dc.identifier.doi | 10.1145/3582437.3587183 | pt_PT |
dc.identifier.isbn | 978-1-4503-9855-8 | |
dc.identifier.uri | http://hdl.handle.net/10400.1/20238 | |
dc.language.iso | eng | pt_PT |
dc.peerreviewed | yes | pt_PT |
dc.publisher | Association for Computing Machinery | pt_PT |
dc.relation | Algarve Centre for Marine Sciences | |
dc.relation | Instituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa | |
dc.relation | Algarve Centre for Marine Sciences | |
dc.relation | Centre for Marine and Environmental Research | |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
dc.subject | Height-map | pt_PT |
dc.subject | Deep Learning | pt_PT |
dc.subject | Image-to-Image Translation | pt_PT |
dc.subject | GAN | pt_PT |
dc.subject | Conditional GAN | pt_PT |
dc.title | Dual critic conditional wasserstein gAN for height-map generation | pt_PT |
dc.type | journal article | |
dspace.entity.type | Publication | |
oaire.awardTitle | Algarve Centre for Marine Sciences | |
oaire.awardTitle | Instituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa | |
oaire.awardTitle | Algarve Centre for Marine Sciences | |
oaire.awardTitle | Centre for Marine and Environmental Research | |
oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04326%2F2020/PT | |
oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50021%2F2020/PT | |
oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F04326%2F2020/PT | |
oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/LA%2FP%2F0101%2F2020/PT | |
oaire.citation.endPage | 4 | pt_PT |
oaire.citation.startPage | 1 | pt_PT |
oaire.citation.title | FDG '23: Proceedings of the 18th International Conference on the Foundations of Digital Games | pt_PT |
oaire.fundingStream | 6817 - DCRRNI ID | |
oaire.fundingStream | 6817 - DCRRNI ID | |
oaire.fundingStream | 6817 - DCRRNI ID | |
oaire.fundingStream | 6817 - DCRRNI ID | |
person.familyName | Dias | |
person.givenName | João | |
person.identifier.ciencia-id | 541C-36A9-F1A0 | |
person.identifier.orcid | 0000-0002-1653-1821 | |
project.funder.identifier | http://doi.org/10.13039/501100001871 | |
project.funder.identifier | http://doi.org/10.13039/501100001871 | |
project.funder.identifier | http://doi.org/10.13039/501100001871 | |
project.funder.identifier | http://doi.org/10.13039/501100001871 | |
project.funder.name | Fundação para a Ciência e a Tecnologia | |
project.funder.name | Fundação para a Ciência e a Tecnologia | |
project.funder.name | Fundação para a Ciência e a Tecnologia | |
project.funder.name | Fundação para a Ciência e a Tecnologia | |
rcaap.rights | openAccess | pt_PT |
rcaap.type | article | pt_PT |
relation.isAuthorOfPublication | 66c729e3-99f2-4ddc-8da4-7c66e590800b | |
relation.isAuthorOfPublication.latestForDiscovery | 66c729e3-99f2-4ddc-8da4-7c66e590800b | |
relation.isProjectOfPublication | fafa76a6-2cd2-4a6d-a3c9-772f34d3b91f | |
relation.isProjectOfPublication | 0b14d63a-8f78-4e31-8a86-b72e1f07871f | |
relation.isProjectOfPublication | 15f91d45-e070-47d8-b6b8-efd4de31d9a8 | |
relation.isProjectOfPublication | 794d4c77-c731-471e-bc96-5a41dcd3d872 | |
relation.isProjectOfPublication.latestForDiscovery | 794d4c77-c731-471e-bc96-5a41dcd3d872 |