Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟴𝟲 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗦𝘁𝘆𝗹𝗲𝗚𝗔𝗡𝟯: Alias-Free Generative Adversarial Networks by NVIDIA AI Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published NeuroIPS2021 with 3 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/erfRSARB Code: https://lnkd.in/eHb57Ad5 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner.  🔸 This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of depicted objects. We trace the root cause to careless signal processing that causes aliasing 🔸 in the generator network. Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process.  🔸 The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales. Our results pave the way for generative models better suited for video and animation. #computervision #artificialintelligence #innovation