公开(公告)号：US11308582B2

公开(公告)日：2022-04-19

申请号：US16844951

申请日：2020-04-09

Applicant: Apple Inc.

Inventor： Jim Chen Chou ,  Chenge Li ,  Yun Gong

IPC: G06K9/40 ,  G06T3/40 ,  G06N3/04 ,  G06T5/50

Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.

公开(公告)号：US20220270208A1

公开(公告)日：2022-08-25

申请号：US17721988

申请日：2022-04-15

Applicant: Apple Inc.

Inventor： Jim Chen Chou ,  Chenge Li ,  Yun Gong

IPC: G06T3/40 ,  G06N3/04 ,  G06T5/50

Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.

公开(公告)号：US20200294196A1

公开(公告)日：2020-09-17

申请号：US16844951

申请日：2020-04-09

Applicant: Apple Inc.

Inventor： Jim Chen Chou ,  Chenge Li ,  Yun Gong

IPC: G06T3/40 ,  G06N3/04 ,  G06T5/50

Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.

公开(公告)号：US11748850B2

公开(公告)日：2023-09-05

申请号：US17721988

申请日：2022-04-15

Applicant: Apple Inc.

Inventor： Jim Chen Chou ,  Chenge Li ,  Yun Gong

IPC: G06T3/40 ,  G06T5/50 ,  G06N3/045

CPC classification number: G06T3/4053 ,  G06N3/045 ,  G06T3/4007 ,  G06T5/50

Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.

公开(公告)号：US20200043135A1

公开(公告)日：2020-02-06

申请号：US16056346

申请日：2018-08-06

Applicant: Apple Inc.

Inventor： Jim Chen Chou ,  Chenge Li ,  Yun Gong

IPC: G06T3/40 ,  G06T5/50 ,  G06N3/04

Abstract: Embodiments relate to a super-resolution engine that converts a lower resolution input image into a higher resolution output image. The super-resolution engine includes a directional scaler, an enhancement processor, a feature detection processor, a blending logic circuit, and a neural network. The directional scaler generates directionally scaled image data by upscaling the input image. The enhancement processor generates enhanced image data by applying an example-based enhancement, a peaking filter, or some other type of non-neural network image processing scheme to the directionally scaled image data. The feature detection processor determines features indicating properties of portions of the directionally scaled image data. The neural network generates residual values defining differences between a target result of the super-resolution enhancement and the directionally scaled image data. The blending logic circuit blends the enhanced image data with the residual values according to the features.