Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟴𝟰 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗛𝗲𝗮𝗱𝗚𝗔𝗡:One-shot Neural Head Synthesis and Editing by Imperial College London Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published ICCV2021 with 76 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/ePNEu6Xv Code : https://lnkd.in/e8YP9CbM ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Recent attempts to solve the problem of head reenactment using a single reference image have shown promising results. However, most of them either perform poorly in terms of photo-realism, or fail to meet the identity preservation problem, or do not fully transfer the driving pose and expression.  🔸 We propose HeadGAN, a novel system that conditions synthesis on 3D face representations, which can be extracted from any driving video and adapted to the facial geometry of any reference image, disentangling identity from expression. We further improve mouth movements, by utilizing audio features as a complementary input. The 3D face representation enables HeadGAN to be further used as an efficient method for compression and reconstruction and a tool for expression and poses editing. #computervision #artificialintelligence #innovation