发明授权
- 专利标题: Regression-based learning model for image upscaling
- 专利标题(中): 基于回归的图像增大学习模型
-
申请号: US13565334申请日: 2012-08-02
-
公开(公告)号: US08655109B2公开(公告)日: 2014-02-18
- 发明人: Zhe Lin , Scott D. Cohen , Jen-Chan Chien , Sarah A. Kong , Jianchao Yang
- 申请人: Zhe Lin , Scott D. Cohen , Jen-Chan Chien , Sarah A. Kong , Jianchao Yang
- 申请人地址: US CA San Jose
- 专利权人: Adobe Systems Incorporated
- 当前专利权人: Adobe Systems Incorporated
- 当前专利权人地址: US CA San Jose
- 代理机构: Wolfe-SBMC
- 主分类号: G06K9/32
- IPC分类号: G06K9/32 ; G06K9/00
摘要:
Methods and systems for a regression-based learning model in image upscaling are disclosed. In one embodiment, a set of image patch pairs for each of a set of images is generated. Each of the image patch pairs contains a natural image and a corresponding downscaled lower-resolution image. A regression model based at least in part on the set of image patch pairs is defined. The regression model represents a gradient of a function of the downscaled lower-resolution image. An image is upscaled based at least in part on the regression model.
公开/授权文献
- US20130034313A1 Regression-Based Learning Model for Image Upscaling 公开/授权日:2013-02-07
信息查询