Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟵𝟴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-map by Vision AI Lab, AI Center, NCSOFT Follow me for a similar post: Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published in ARXIV2022. 🤝 Present a novel conditional landscape synthesis framework, StyLandGAN, with depth map which is capable of expressing ridge and scale representation. We show that our ‘2-phase inference’ makes it possible to acquire diverse structure and style of landscape images in a row. Our framework exceeds previous I2I translation method in image quality, image diversity, and depth accuracy. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 👉 Despite recent success in conditional image synthesis, prevalent input conditions such as semantics and edges are not clear enough to express `Linear (Ridges)' and `Planar (Scale)' representations. 👉 To address this problem, we propose a novel framework StyLandGAN, which synthesizes desired landscape images using a depth map which has higher expressive power. 👉 Our StyleLandGAN is extended from the unconditional generation model to accept input conditions. 👉 We also propose a '2-phase inference' pipeline which generates diverse depth maps and shifts local parts so that it can easily reflect user's intend. 👉 As a comparison, we modified the existing semantic image synthesis models to accept a depth map as well. 👉 Experimental results show that our method is superior to existing methods in quality, diversity, and depth-accuracy. #computervision #artificialintelligence  #deeplearning #data #technology