Invention Grant
- Patent Title: Machine-learning based technique for fast image enhancement
-
Application No.: US15843345Application Date: 2017-12-15
-
Publication No.: US10579908B2Publication Date: 2020-03-03
- Inventor: Jiawen Chen , Samuel Hasinoff , Michael Gharbi , Jonathan Barron
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: McDonnell Boehnen Hulbert & Berghoff LLP
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06K9/66 ; G06T3/00 ; G06T3/40 ; G06T5/00 ; H04N5/232

Abstract:
Systems and methods described herein may relate to image transformation utilizing a plurality of deep neural networks. An example method includes receiving, at a mobile device, a plurality of image processing parameters. The method also includes causing an image sensor of the mobile device to capture an initial image and receiving, at a coefficient prediction neural network at the mobile device, an input image based on the initial image. The method further includes determining, using the coefficient prediction neural network, an image transformation model based on the input image and at least a portion of the plurality of image processing parameters. The method additionally includes receiving, at a rendering neural network at the mobile device, the initial image and the image transformation model. Yet further, the method includes generating, by the rendering neural network, a rendered image based on the initial image, according to the image transformation model.
Public/Granted literature
- US20190188535A1 Machine-Learning Based Technique for Fast Image Enhancement Public/Granted day:2019-06-20
Information query