Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟰𝟳 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Mixed DualStyleGAN: Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer by Nanyang Technological University Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published arxiv2022. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ➡️ Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data. ➡️ In this paper, we explore more challenging exemplar-based high-resolution portrait style transfer by introducing a novel DualStyleGAN with flexible control of dual styles of the original face domain and the extended artistic portrait domain. ➡️ Different from StyleGAN, DualStyleGAN provides a natural way of style transfer by characterizing the content and style of a portrait with an intrinsic style path and a new extrinsic style path, respectively. ➡️ The delicately designed extrinsic style path enables our model to modulate both the color and complex structural styles hierarchically to precisely pastiche the style example. ➡️ Furthermore, a novel progressive fine-tuning scheme is introduced to smoothly transform the generative space of the model to the target domain, even with the above modifications on the network architecture. ➡️ Experiments demonstrate the superiority of DualStyleGAN over state-of-the-art methods in high-quality portrait style transfer and flexible style control. #computervision #artificialintelligence #technology