Konferans bildirisi Açık Erişim
Gokay, Dilara; Simsar, Enis; Atici, Efehan; Ahmetoglu, Alper; Yuksel, Atif Emre; Yanardag, Pinar
<?xml version='1.0' encoding='UTF-8'?> <record xmlns="http://www.loc.gov/MARC21/slim"> <leader>00000nam##2200000uu#4500</leader> <datafield tag="245" ind1=" " ind2=" "> <subfield code="a">Graph2Pix: A Graph-Based Image to Image Translation Framework</subfield> </datafield> <datafield tag="024" ind1=" " ind2=" "> <subfield code="a">10.1109/ICCVW54120.2021.00227</subfield> <subfield code="2">doi</subfield> </datafield> <controlfield tag="001">237762</controlfield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="a">user-tubitak-destekli-proje-yayinlari</subfield> </datafield> <datafield tag="520" ind1=" " ind2=" "> <subfield code="a">In this paper, we propose a graph-based image-to-image translation framework for generating images. We use rich data collected from the popular creativity platform Artbreeder', where users interpolate multiple GAN-generated images to create artworks. This unique approach of creating new images leads to a tree-like structure where one can track historical data about the creation of a particular image. Inspired by this structure, we propose a novel graph-to-image translation model called Graph2Pix, which takes a graph and corresponding images as input and generates a single image as output. Our experiments show that Graph2Pix is able to outperform several image-to-image translation frameworks on benchmark metrics, including LPIPS (with a 25% improvement) and human perception studies (n = 60), where users preferred the images generated by our method 81.5% of the time.</subfield> </datafield> <datafield tag="650" ind1="1" ind2="7"> <subfield code="2">opendefinition.org</subfield> <subfield code="a">cc-by</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="a">Simsar, Enis</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="u">Bogazici Univ, Bebek, Turkey</subfield> <subfield code="a">Atici, Efehan</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="u">Bogazici Univ, Bebek, Turkey</subfield> <subfield code="a">Ahmetoglu, Alper</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="u">Bogazici Univ, Bebek, Turkey</subfield> <subfield code="a">Yuksel, Atif Emre</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="u">Bogazici Univ, Bebek, Turkey</subfield> <subfield code="a">Yanardag, Pinar</subfield> </datafield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="b">conferencepaper</subfield> <subfield code="a">publication</subfield> </datafield> <datafield tag="542" ind1=" " ind2=" "> <subfield code="l">open</subfield> </datafield> <datafield tag="100" ind1=" " ind2=" "> <subfield code="u">Tech Univ Munich, Munich, Germany</subfield> <subfield code="a">Gokay, Dilara</subfield> </datafield> <datafield tag="711" ind1=" " ind2=" "> <subfield code="a">2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)</subfield> </datafield> <datafield tag="260" ind1=" " ind2=" "> <subfield code="c">2021-01-01</subfield> </datafield> <controlfield tag="005">20221007100117.0</controlfield> <datafield tag="909" ind1="C" ind2="O"> <subfield code="o">oai:aperta.ulakbim.gov.tr:237762</subfield> <subfield code="p">user-tubitak-destekli-proje-yayinlari</subfield> </datafield> <datafield tag="856" ind1="4" ind2=" "> <subfield code="z">md5:355f1be7388c5c96412f21895b0e9ad5</subfield> <subfield code="s">226</subfield> <subfield code="u">https://aperta.ulakbim.gov.trrecord/237762/files/bib-54bf792e-8fd2-4341-a67a-47097a6dcaf8.txt</subfield> </datafield> <datafield tag="540" ind1=" " ind2=" "> <subfield code="u">http://www.opendefinition.org/licenses/cc-by</subfield> <subfield code="a">Creative Commons Attribution</subfield> </datafield> </record>
Görüntülenme | 20 |
İndirme | 5 |
Veri hacmi | 1.1 kB |
Tekil görüntülenme | 18 |
Tekil indirme | 5 |