公开(公告)号：US20160292824A1

公开(公告)日：2016-10-06

申请号：US14783763

申请日：2014-04-11

Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH

Inventor： Zhengguo LI ,  Jinghong ZHENG ,  Zijian ZHU ,  Shiqian WU ,  Wei YAO ,  Susanto RAHARDJA

IPC: G06T5/00 ,  G06T7/00 ,  G06T3/20

CPC classification number: G06T5/00 ,  G06T3/20 ,  G06T5/002 ,  G06T5/003 ,  G06T5/50 ,  G06T7/13 ,  G06T2207/10016 ,  G06T2207/20012 ,  G06T2207/20024 ,  G06T2207/20028 ,  G06T2207/20076 ,  G06T2207/20192 ,  H04N1/4092

Abstract: In various embodiments of the present disclosure, there is provided a method for processing an input image. The method includes generating a base layer portion and a detail layer portion from the input image by carrying out a linear transformation of pixels of a guidance image, and determining, for each of the pixels of the guidance image, a variance of the pixels in a surrounding window of pixels. Further, the method includes determining, for each of the pixels of the guidance image, a weight value of the pixels based on the determined variance, wherein the pixels are weighted in the linear transformation according to the determined weight value. Accordingly, a system for processing an input image is also provided.

Abstract translation: 在本公开的各种实施例中，提供了一种用于处理输入图像的方法。 该方法包括通过执行引导图像的像素的线性变换从输入图像生成基本层部分和细节层部分，并且对于引导图像的每个像素，确定像素的方差 周围的像素窗口。 此外，该方法包括基于所确定的方差来确定针对引导图像的每个像素的像素的权重值，其中根据确定的权重值在线性变换中对像素进行加权。 因此，还提供了一种用于处理输入图像的系统。