1 Ocak 2022 Konferans bildirisi Açık Erişim

Kocasari, Umut; Dirik, Alara; Tiftikci, Mert; Yanardag, Pinar

MARC21 XML

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">user-tubitak-destekli-proje-yayinlari</subfield>
    <subfield code="o">oai:aperta.ulakbim.gov.tr:254637</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">Discovering meaningful directions in the latent space of GANs to manipulate semantic attributes typically requires large amounts of labeled data. Recent work aims to overcome this limitation by leveraging the power of Contrastive Language-Image Pm-training (CLIP), a joint text-image model. While promising, these methods require several hours of preprocessing or training to achieve the desired manipulations. In this paper, we present StyleMC, a fast and efficient method for text-driven image generation and manipulation. StyleMC uses a CLIP-based loss and an identity loss to manipulate images via a single text prompt without significantly affecting other attributes. Unlike prior work, StyleMC requires only a few seconds of training per text prompt to find stable global directions, does not require prompt engineering and can be used with any pre-trained StyleGAN2 model. We demonstrate the effectiveness of our method and compare it to state-of-the-art methods. Our code can be found at http: // catlab-team. github. io/stylemc.</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="a">2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Creative Commons Attribution</subfield>
    <subfield code="u">http://www.opendefinition.org/licenses/cc-by</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Kocasari, Umut</subfield>
    <subfield code="u">Bogazici Univ, Istanbul, Turkey</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="z">md5:10deaa5f659f7f3c1bdc61ef565b3923</subfield>
    <subfield code="s">216</subfield>
    <subfield code="u">https://aperta.ulakbim.gov.trrecord/254637/files/bib-406984f3-b67f-4bcf-846d-2779e8496106.txt</subfield>
  </datafield>
  <controlfield tag="005">20230728212621.0</controlfield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2022-01-01</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1109/WACV51458.2022.00350</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Dirik, Alara</subfield>
    <subfield code="u">Bogazici Univ, Istanbul, Turkey</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Tiftikci, Mert</subfield>
    <subfield code="u">Bogazici Univ, Istanbul, Turkey</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Yanardag, Pinar</subfield>
    <subfield code="u">Bogazici Univ, Istanbul, Turkey</subfield>
  </datafield>
  <controlfield tag="001">254637</controlfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-tubitak-destekli-proje-yayinlari</subfield>
  </datafield>
</record>