专利检索 ap:("Zhan Ma" OR "Haojie Liu" OR "Tong Chen" OR "Qiu Shen" OR "Tao Yue") AND inv:"Haojie Liu" 第 1 页

1.

发明申请
Methods And Apparatuses For Learned Image Compression 审中-公开

公开(公告)号：US20200160565A1

公开(公告)日：2020-05-21

申请号：US16689062

申请日：2019-11-19

申请人： Zhan Ma , Haojie Liu , Tong Chen , Qiu Shen , Tao Yue

发明人： Zhan Ma , Haojie Liu , Tong Chen , Qiu Shen , Tao Yue

IPC分类号： G06T9/00 , G06N3/04 , H04N19/90

摘要： A learned image compression system increases compression efficiency by using a novel conditional context model with embedded autoregressive neighbors and hyperpriors, which can accurately estimate the entropy rate for rate distortion optimization. Generalized Divisive Normalization (GDN) in Residual Neural Network is used in the encoder and decoder networks for fast convergence rate and efficient feature representation.