GAN-Assisted YUV Pixel Art Generation
dc.contributor.author | Jiang, Zhouyang | |
dc.contributor.author | Sweetser Kyburz, Penny | |
dc.date.accessioned | 2021-09-30T04:01:34Z | |
dc.date.issued | 2021-12 | |
dc.description.abstract | Procedural Content Generation (PCG) in games has grown in popularity in recent years, with Generative Adversarial Networks (GANs) providing a promising option for applying PCG for game artistic asset generation. In this paper, we introduce a model that uses GANs and the YUV colour encoding system for automatic colouring of game assets. In this model, conditional GANs in Pix2Pix architecture are chosen as the main structure and the YUV colour encoding system is used for data preprocessing and result visualisation. We experimented with parameter settings (number of epochs, activation functions, optimisers) to optimise output. Our experimental results show that the proposed model can generate evenly coloured outputs for both small and larger datasets. | en_AU |
dc.format.mimetype | application/pdf | en_AU |
dc.identifier.issn | 0302-9743 | en_AU |
dc.identifier.uri | http://hdl.handle.net/1885/249084 | |
dc.language.iso | en_AU | en_AU |
dc.provenance | https://www.springernature.com/gp/open-research/policies/book-policies..."Authors whose work is accepted for publication in a non-open access Springer or Palgrave Macmillan book are permitted to self-archive the accepted manuscript (AM), on their own personal website and/or in their funder or institutional repositories, for public release after an embargo period of 12 months for proceedings." from the publisher site (as at 30 Sept 2021) | en_AU |
dc.publisher | Springer | en_AU |
dc.relation.ispartof | Australasian Joint Conference on Artificial Intelligence | en_AU |
dc.rights | © 2021 The Author(s) | en_AU |
dc.subject | Generative Adversarial Networks | en_AU |
dc.subject | Art Generation | en_AU |
dc.subject | Video Games | en_AU |
dc.subject | Procedural Content Generation | en_AU |
dc.subject | Pixel Art | en_AU |
dc.title | GAN-Assisted YUV Pixel Art Generation | en_AU |
dc.type | Conference paper | en_AU |
dcterms.accessRights | Open Access | en_AU |
local.bibliographicCitation.lastpage | 12 | en_AU |
local.bibliographicCitation.startpage | 1 | en_AU |
local.contributor.affiliation | Sweetser, P., School of Computing, CECS, The Australian National University | en_AU |
local.contributor.authoremail | penny.kyburz@anu.edu.au | en_AU |
local.contributor.authoruid | u1027166 | en_AU |
local.identifier.essn | 1611-3349 | en_AU |
local.identifier.uidSubmittedBy | u1072166 | en_AU |
local.publisher.url | https://link.springer.com/ | en_AU |
local.type.status | Submitted Version | en_AU |