BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171537Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T164100
DTEND;TZID=Asia/Tokyo:20241205T165300
UID:siggraphasia_SIGGRAPH Asia 2024_sess137_papers_484@linklings.com
SUMMARY:HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Sy
 nthesis and Manipulation
DESCRIPTION:Abdul Basit Anees (Koç University), Ahmet Canberk Baykal (Univ
 ersity of Cambridge), Muhammed Burak Kizil (Koç University), Duygu Ceylan 
 (Adobe Research), Erkut Erdem (Hacettepe University), and Aykut Erdem (Koç
  University)\n\nGenerative Adversarial Networks (GANs), particularly Style
 GAN and its variants, have demonstrated remarkable capabilities in generat
 ing highly realistic images. Despite their success, adapting these models 
 to diverse tasks such as domain adaptation, reference-guided synthesis, an
 d text-guided manipulation with limited training data remains challenging.
  Towards this end, in this study, we present a novel framework that signif
 icantly extends the capabilities of a pre-trained StyleGAN by integrating 
 CLIP space via hypernetworks. This integration allows dynamic adaptation o
 f StyleGAN to new domains defined by reference images or textual descripti
 ons. Additionally, we introduce a CLIP-guided discriminator that enhances 
 the alignment between generated images and target domains, ensuring superi
 or image quality. Our approach demonstrates unprecedented flexibility, ena
 bling text-guided image manipulation without the need for text-specific tr
 aining data and facilitating seamless style transfer. Comprehensive qualit
 ative and quantitative evaluations confirm the robustness and superior per
 formance of our framework compared to existing methods.\n\nRegistration Ca
 tegory: Full Access, Full Access Supporter\n\nLanguage Format: English Lan
 guage\n\nSession Chair: Michael Rubinstein (Google)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_484&sess=sess137
END:VEVENT
END:VCALENDAR