Abstract: Provided is an image sensor including a pixel array including pixels respectively including sub-pixels connected to a floating diffusion node, a first sub-pixel of a first pixel and a second sub-pixel of a second pixel corresponding to a first microlens, a readout circuit configured to generate first image data based on a first pixel signal output from the first sub-pixel and a second pixel signal output from the second sub-pixel, and generate second image data based on a third pixel signal output from sub-pixels, other than the first sub-pixel, of the sub-pixels of the first pixel and a fourth pixel signal output from sub-pixels, other than the second sub-pixel, of the sub-pixels of the second pixel, and an image signal processor configured to generate high dynamic range image data based on the first and second image data, and generate auto-focus information based on the first image data.

Abstract: An image sensor includes a pixel array including a plurality of unit pixels configured to receive light of a color filter array having a first color pattern of size k×l arranged therein, where k and l are natural numbers of 3 or more, the image sensor configured to generate first image data including the first color pattern and an image signal processor (ISP) configured to generate second image data including a second color pattern of size p×q, by remosaicing the first image data, where p and q are natural numbers of 2 or more, where a size of the second color pattern is smaller than a size of the first color pattern, and the image sensor is configured to transmit the second image data an application processor that is external to the image sensor.

Abstract: An image processing method performed by an image processing device may include receiving input image data from an image sensor, selecting a convolution filter corresponding to each unit region from among a plurality of convolution filters based on color pattern information of the input image data, and generating, based on the selected convolution filter, a first image to be displayed from the input image data.

Abstract: There is provided an image sensor including a pixel array including a plurality of pixels, a readout circuit that outputs first pixel data and second pixel data based on an output signal of the pixel array, and an image signal processor that generates third pixel data by restoring at least a portion of saturated pixel data of the first pixel data based on the second pixel data, and outputs the HDR image data based on the second pixel data and the third pixel data. At least a portion of the first pixel data may have a higher intensity value than the second pixel data.

Abstract: An image processing network module, an image processing device, and a method of operating the image processing device are provided. The image processing network module includes an encoder configured to receive input image data and change a bit depth of the input image data to generate first image data, a quantization network configured to quantize the first image data to generate second image data, and a decoder configured to receive the second image data and change a bit depth of the second image data to generate output image data.

Abstract: An image processing apparatus includes a camera configured to generate first image data, a pre-processor configured to generate second image data based on performing a pre-processing operation on the first image data, a neural network processor configured to generate third image data based on performing an image processing operation on the second image data based on using a neural network model trained to perform one or more particular image processing operations, and a main processor configured to generate corrected image data based on performing a post-processing operation on the third image data.

Abstract: An image processing method performed by an image processing device may include receiving input image data from an image sensor, selecting a convolution filter corresponding to each unit region from among a plurality of convolution filters based on color pattern information of the input image data, and generating, based on the selected convolution filter, a first image to be displayed from the input image data.

Abstract: An image processing apparatus includes a camera configured to generate first image data, a pre-processor configured to generate second image data based on performing a pre-processing operation on the first image data, a neural network processor configured to generate third image data based on performing an image processing operation on the second image data based on using a neural network model trained to perform one or more particular image processing operations, and a main processor configured to generate corrected image data based on performing a post-processing operation on the third image data.

Abstract: A lens shading correction method includes providing lens shading correction profile data; calculating an intensity values of light passing through each of one or more visible light pass filters and each of one or more infrared light pass filters; calculating an average of the intensity values of the light passing through the one or more visible light pass filters; calculating an average of the intensity values of the light passing through the one or more infrared light pass filters; calculating a normalized intensity value of the light passing through the one or more infrared light pass filters, based on the calculated averages; adjusting one or more lens shading correction coefficients included in the lens shading correction profile data and each having a value varying depending on a frequency element of light, based on the calculated normalized intensity value; and correcting lens shading by using the adjusted lens shading correction coefficient.

Abstract: A lens shading correction method includes providing lens shading correction profile data; calculating an intensity values of light passing through each of one or more visible light pass filters and each of one or more infrared light pass filters; calculating an average of the intensity values of the light passing through the one or more visible light pass filters; calculating an average of the intensity values of the light passing through the one or more infrared light pass filters; calculating a normalized intensity value of the light passing through the one or more infrared light pass filters, based on the calculated averages; adjusting one or more lens shading correction coefficients included in the lens shading correction profile data and each having a value varying depending on a frequency element of light, based on the calculated normalized intensity value; and correcting lens shading by using the adjusted lens shading correction coefficient.