Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟲𝟮 Computer Vision Learning 𝗣𝗤-𝗡𝗘𝗧: A Generative Part Seq2Seq Network for 3D Shapes by Peking University, National University of Defense Technology, and Simon Fraser University Follow me for similar post:  @🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR 2020 with over 19 citations. 🔸 It Outperforms with the 3D-PRNN, etc. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/ebMWKgp code : https://lnkd.in/eVPk-UQ ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 PQ-NET, a deep neural network that represents and generates 3D shapes via sequential part assembly.  🔸 The input to PQ-NETnetwork is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. 🔸 The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly.  #computervision #artificialintelligence #technology