Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟳𝟵 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗦𝗲𝗮𝗺𝗹𝗲𝘀𝘀𝗚𝗔𝗡: 𝗦𝗲𝗹𝗳-𝗦𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗦𝘆𝗻𝘁𝗵𝗲𝘀𝗶𝘀 𝗼𝗳 𝗧𝗶𝗹𝗲𝗮𝗯𝗹𝗲 𝗧𝗲𝘅𝘁𝘂𝗿𝗲 𝗠𝗮𝗽𝘀 𝗯𝘆 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝗱𝗮𝗱 𝗖𝗮𝗿𝗹𝗼𝘀, 𝗦𝗽𝗮𝗶𝗻  Follow me for a similar post: @🇮🇳 Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: 𝗦𝗲𝗮𝗺𝗹𝗲𝘀𝘀𝗚𝗔𝗡: 𝗦𝗲𝗹𝗳-𝗦𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗦𝘆𝗻𝘁𝗵𝗲𝘀𝗶𝘀 𝗼𝗳 𝗧𝗶𝗹𝗲𝗮𝗯𝗹𝗲 𝗧𝗲𝘅𝘁𝘂𝗿𝗲 𝗠𝗮𝗽𝘀 🔸 This paper is published IEEE Transactions 2022. 🔸 Proposed a deep parametric texture synthesis framework capable of synthesizing textures into tileable single-tiles, by combining recent advances on deep texture synthesis, adversarial neural networks and latent spaces manipulation.  ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 We present SeamlessGAN, a method capable of automatically generating tileable texture maps from a single input exemplar. In contrast to most existing methods, focused solely on solving the synthesis problem, our work tackles both problems, synthesis and tileability, simultaneously.  🔸 Our key idea is to realize that tiling a latent space within a generative network trained using adversarial expansion techniques produces outputs with continuity at the seam intersection that can be then be turned into tileable images by cropping the central area.  🔸 Since not every value of the latent space is valid to produce high-quality outputs, we leverage the discriminator as a perceptual error metric capable of identifying artifact-free textures during a sampling process.  🔸 Further, in contrast to previous work on deep texture synthesis, our model is designed and optimized to work with multi-layered texture representations, enabling textures composed of multiple maps such as albedo, normals, etc. We extensively test our design choices for the network architecture, loss function and sampling parameters. We show qualitatively and quantitatively that our approach outperforms previous methods and works for textures of different types. #computervision #artificialintelligence #technology