Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟵𝟰 Computer Vision Learning 𝗦𝘁𝘆𝗹𝗲𝗠𝗮𝗽𝗚𝗔𝗡: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing by Seoul National University and NAVER AI LAB Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR2021 with over 2 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/gG8Yxwr Code : https://lnkd.in/gpzBy3U ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder.  🔸 The Author proposes StyleMapGAN: the intermediate latent space has spatial dimensions, and a spatially variant modulation replaces AdaIN. It makes the embedding through an encoder more accurate than existing optimization-based methods while maintaining the properties of GANs.  🔸Experimental results demonstrate that our method significantly outperforms state-of-the-art models in various image manipulation tasks such as local editing and image interpolation. Last but not least, conventional editing methods on GANs are still valid on our StyleMapGAN.  #computervision #artificialintelligence #deeplearning