ð——ð—®ð˜†-ðŸ°ðŸµðŸ´ ð—–ð—¼ð—ºð—½ð˜‚ð˜ð—²ð—¿ ð—©ð—¶ð˜€ð—¶ð—¼ð—» ð—Ÿð—²ð—®ð—¿ð—»ð—¶ð—»ð—´ 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 ------------------------------------------------------------------- ð—œð—»ð˜ð—²ð—¿ð—²ð˜€ð˜ð—¶ð—»ð—´ ð—™ð—®ð—°ð˜ð˜€ : 🔸 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. ------------------------------------------------------------------- ð—œð— ð—£ð—¢ð—¥ð—§ð—”ð—¡ð—–𗘠👉 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
Sign in to view more content
Create your free account or sign in to continue your search
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.