US 11,893,711 B2
Neural network-based image processing with artifact compensation
Jim C. Chou, San Jose, CA (US); and Yun Gong, Cupertino, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Jun. 15, 2022, as Appl. No. 17/841,387.
Application 17/841,387 is a continuation of application No. 17/000,260, filed on Aug. 21, 2020, granted, now 11,367,167.
Prior Publication US 2022/0309616 A1, Sep. 29, 2022
Int. Cl. G06T 3/40 (2006.01); G06T 7/11 (2017.01); G06T 5/50 (2006.01); G06T 5/00 (2006.01)
CPC G06T 5/001 (2013.01) [G06T 3/4046 (2013.01); G06T 3/4053 (2013.01); G06T 5/50 (2013.01); G06T 7/11 (2017.01); G06T 2207/20084 (2013.01); G06T 2207/20192 (2013.01); G06T 2207/20221 (2013.01)] 19 Claims
OG exemplary drawing
 
1. An electronic device, comprising:
a neural network configured to receive and process image data;
enhancement circuitry configured to receive and enhance the image data; and
blending circuitry that comprises a first multiplier and that is configured to:
receive the processed image data;
receive the enhanced image data;
receive edge information related to the image data;
receive an image plane of the image data;
determine a first weight in a first lookup table based at least in part on the edge information and based at least in part on a neural network enable signal;
scale the processed image data based on the first weight using the first multiplier to generate a processed component;
determine a second weight in a second lookup table based at least in part on the edge information;
scale the enhanced image data based on the second weight; and
add the scaled processed image data and the scaled enhanced image data together.