CPC G06T 11/001 (2013.01) [G06N 3/04 (2013.01); G06T 11/60 (2013.01); G06V 10/82 (2022.01); G06V 30/194 (2022.01); G06F 16/51 (2019.01); G06V 10/454 (2022.01)] | 20 Claims |
1. A method comprising:
accessing an image generated using an image sensor on a device;
generating, using one or more processors of the device, image data of the image by using a fully connected neural network layer that outputs the image data into a convolutional layer, the image data comprising rank one image matrices;
generating a modified image from the image data using a convolutional neural network (CNN), the CNN configured with the convolution layer having rank one convolution kernel matrices generated for a sample set of points of an inferred matrix that is configured to apply an image modification, an output of the convolution layer generated based on the rank one image matrices and the rank one convolution kernel matrices, the rank one image matrices from the image data being generated for the sample set of points of the inferred matrix; and
storing the modified image in memory of the device.
|