Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟲𝟬 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝘆 𝗼𝗳 𝗜𝗹𝗹𝗶𝗻𝗼𝗶𝘀 𝗵𝗮𝘀 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱 𝗝𝗼𝗝𝗼𝗚𝗔𝗡: 𝗢𝗻𝗲 𝗦𝗵𝗼𝘁 𝗙𝗮𝗰𝗲 𝗦𝘁𝘆𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻 Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: 𝗝𝗼𝗝𝗼𝗚𝗔𝗡: 𝗢𝗻𝗲 𝗦𝗵𝗼𝘁 𝗙𝗮𝗰𝗲 𝗦𝘁𝘆𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻 🔸 This paper is published in arxiv2021. 🔸 Stop spending your time collecting data! We present JoJoGAN (named after the best anime JoJo’s Bizarre Adventure, the inspiration for this work), a framework for arbitrary one-shot face stylization. Given a single input style reference, we are able to apply the style onto any input image, carefully preserving detailed style characteristics such as eye appearences, proportions, etc. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🎄 While there have been recent advances in few-shot image stylization, these methods fail to capture stylistic details that are obvious to humans. ⛄ Details such as the shape of the eyes, the boldness of the lines, are especially difficult for a model to learn, especially so under a limited data setting. 🎄 In this work, we aim to perform one-shot image stylization that gets the details right. ☃️ Given a reference style image, we approximate paired real data using GAN inversion and finetune a pretrained StyleGAN using that approximate paired data. 🎄We then encourage the StyleGAN to generalize so that the learned style can be applied to all other images. #computervision #artificialintelligence #innovation