- 专利标题: Image upsampling system, training method thereof and image upsampling method
-
申请号: US15518404申请日: 2016-03-02
-
公开(公告)号: US10019642B1公开(公告)日: 2018-07-10
- 发明人: Pablo Navarrete Michelini , Lijie Zhang , Jianmin He
- 申请人: BOE TECHNOLOGY GROUP CO., LTD.
- 申请人地址: CN Beijing
- 专利权人: BOE TECHNOLOGY GROUP CO., LTD.
- 当前专利权人: BOE TECHNOLOGY GROUP CO., LTD.
- 当前专利权人地址: CN Beijing
- 代理机构: Collard & Roe, P.C.
- 优先权: CN201510595656 20150917
- 国际申请: PCT/CN2016/075338 WO 20160302
- 国际公布: WO2017/045374 WO 20170323
- 主分类号: G06K9/46
- IPC分类号: G06K9/46 ; G06N3/04 ; G06N3/08 ; G06K9/62 ; G06T3/40
摘要:
An image upsampling system, a training method thereof and an image upsampling method are provided, the feature images of an image are obtained by using the convolutional network, upsampling processing is performed on the images with the muxer layer to synthesize every n×n feature images in the input signal into a feature image with the resolution amplified by n×n times, in the upsampling procedure with the muxer layer, information of respective feature images in the input signal is recorded in the generated feature image(s) without loss; and thus, every time when the image passes through a muxer layer with an upsampling multiple of n, the image resolution can be increased by n×n times.