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:20250110T023312Z 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:Technical Papers\n\nAbdul Basit Anees (Koç University), Ahmet Canberk Baykal (University of Cambridge), Muhammed Burak Kizil (Koç Univer sity), Duygu Ceylan (Adobe Research), Erkut Erdem (Hacettepe University), and Aykut Erdem (Koç University)\n\nGenerative Adversarial Networks (GANs) , particularly StyleGAN and its variants, have demonstrated remarkable cap abilities in generating highly realistic images. Despite their success, ad apting these models to diverse tasks such as domain adaptation, reference- guided synthesis, and text-guided manipulation with limited training data remains challenging. Towards this end, in this study, we present a novel f ramework that significantly extends the capabilities of a pre-trained Styl eGAN by integrating CLIP space via hypernetworks. This integration allows dynamic adaptation of StyleGAN to new domains defined by reference images or textual descriptions. Additionally, we introduce a CLIP-guided discrimi nator that enhances the alignment between generated images and target doma ins, ensuring superior image quality. Our approach demonstrates unpreceden ted flexibility, enabling text-guided image manipulation without the need for text-specific training data and facilitating seamless style transfer. Comprehensive qualitative and quantitative evaluations confirm the robustn ess and superior performance of our framework compared to existing methods .\n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: Michael Rubinstein (Google) URL:https://asia.siggraph.org/2024/program/?id=papers_484&sess=sess137 END:VEVENT END:VCALENDAR