-
1.发明公开公开(公告)号：US20240029203A1
公开(公告)日：2024-01-25
申请号：US18218017
申请日：2023-07-04
Applicant: MEDIATEK INC.
Inventor： Yu-Syuan Xu , Po-Yu Chen , Wei-Chen Chiu , Ching-Chun Huang , Hsuan Yuan , Shao-Yu Weng
IPC: G06T3/40
CPC classification number: G06T3/4076 , G06T3/4084 , G06T3/4046
Abstract: An arbitrary-scale blind super resolution model has two designs. First, learn dual degradation representations where the implicit and explicit representations of degradation are sequentially extracted from the input low resolution image. Second, process both upsampling and downsampling at the same time, where the implicit and explicit degradation representations are utilized respectively, in order to enable cycle-consistency and train the arbitrary-scale blind super resolution model.
-
2.发明公开公开(公告)号：US20240029201A1
公开(公告)日：2024-01-25
申请号：US18224564
申请日：2023-07-20
Applicant: MEDIATEK INC.
Inventor： Po-Yu Chen , Yu-Syuan Xu , Ching-Chun Huang , Wei-Chen Chiu , Hsuan Yuan , Shao-Yu Weng
CPC classification number: G06T3/4046 , G06T3/4053 , G06T5/002 , G06T5/50 , G06T5/10 , G06T2207/20064 , G06T2207/20081 , G06T2207/20076 , G06T2207/20084
Abstract: A method for generating a high resolution image from a low resolution image includes retrieving a plurality of low resolution image patches from the low resolution image, performing discrete wavelet transform on each low resolution image patch to generate a first image patch with a high frequency on a horizontal axis and a high frequency on a vertical axis, a second image patch with a high frequency on the horizontal axis and a low frequency on the vertical axis, and a third image patch with a low frequency on the horizontal axis and a high frequency on the vertical axis, inputting the three image patches to a dual branch degradation extractor to generate a blur representation and a noise representation, and performing contrastive learning on the blur representation and the noise representation by reducing a blur loss and a noise loss.
-
Search Results
2
records
(took 0.011 seconds)
