A processor-implemented method with image processing includes: providing retouch result candidates of an input image to a user in response to applying vector value candidates to a style vector; determining a vector value of the style vector based on a selection of the user for the retouch result candidates; determining an adjustment parameter set corresponding to the determined vector value of the style vector; and generating a retouch result by adjusting the input image based on the adjustment parameter set.

Provided is an image sensor and an operation method of the image sensor. The image sensor includes a pixel array including a plurality of white pixels, a plurality of color pixels, and a plurality of auto focus (AF) pixels, a first shared pixel including the plurality of white pixels and the plurality of color pixels includes a first conversion gain transistor and a second conversion gain transistor configured to control a conversion gain of the first shared pixel, and a second shared pixel including some of the plurality of white pixels and the plurality of color pixels and at least one AF pixel includes a third conversion gain transistor and a fourth conversion gain transistor configured to control a conversion gain of the second shared pixel. The first conversion gain transistor, the second conversion gain transistor, the third conversion gain transistor, and the fourth conversion gain transistor are connected to different conversion gain control lines, respectively.

Provided is an image sensor and an operation method of the image sensor. The image sensor includes a pixel array including a plurality of white pixels, a plurality of color pixels, and a plurality of auto focus (AF) pixels, a first shared pixel including the plurality of white pixels and the plurality of color pixels includes a first conversion gain transistor and a second conversion gain transistor configured to control a conversion gain of the first shared pixel, and a second shared pixel including some of the plurality of white pixels and the plurality of color pixels and at least one AF pixel includes a third conversion gain transistor and a fourth conversion gain transistor configured to control a conversion gain of the second shared pixel. The first conversion gain transistor, the second conversion gain transistor, the third conversion gain transistor, and the fourth conversion gain transistor are connected to different conversion gain control lines, respectively.

An image processing apparatus comprises a first acquisition unit configured to acquire, based on a luminance distribution in an input image, first control information for controlling characteristics of luminance gradation correction to be applied on the input image, a second acquisition unit configured to acquire, based on the first control information, second control information for controlling characteristics of luminance gradation correction to be applied on the input image, and a correction unit configured to correct luminance gradation of the input image based on the second control information.

An image sensing system includes an image sensor, a sensing controller, an additional unit, and a sensing parameter calculator. The image sensor includes a plurality of unit pixels and configured to generate raw image data indicative an image of an object from pixel signals from the plurality of unit pixels. The sensing controller is configured to control, based on a sensing parameter, a sensing condition of the image sensor for each set of the unit pixels. The parameter addition circuit is configured to obtain a parameter added data by adding the sensing parameter and the raw image data. The sensing parameter calculator is configured to calculate a distribution of pixel values for each set of the unit pixels, calculate an updated sensing parameter based on the distribution of pixel values, and transmit the updated sensing parameter to the sensing controller and the parameter addition circuit.

An electronic device may include: a camera; a display positioned between an object to be photographed by the camera and the camera; a processor connected to the camera and the display; and a memory operatively connected to the processor, wherein the memory stores instructions that, when executed, cause the processor to: receive an original image from the camera; input the original image as an input value to an artificial intelligence model trained for improving image quality, and obtain a correction image from a result value output from the artificial intelligent model; detect a saturated area in which a light source is depicted in the correction image; and obtain a compensation image by blurring a boundary between the saturated area and a periphery thereof in the correction image by using the original image.

An electronic device may include: a camera; a display positioned between an object to be photographed by the camera and the camera; a processor connected to the camera and the display; and a memory operatively connected to the processor, wherein the memory stores instructions that, when executed, cause the processor to: receive an original image from the camera; input the original image as an input value to an artificial intelligence model trained for improving image quality, and obtain a correction image from a result value output from the artificial intelligent model; detect a saturated area in which a light source is depicted in the correction image; and obtain a compensation image by blurring a boundary between the saturated area and a periphery thereof in the correction image by using the original image.

Provided is an image processing apparatus (200), comprising: a communicating unit (202) capable of communicating with each of a plurality of image sensors configured to transmit, in respectively different packets, additional data including region information corresponding to a region set with respect to a captured image for each region and region image data indicating an image for each row corresponding to the region; and a processing unit (204) configured to process, in association with each region, the region image data acquired from each of the plurality of image sensors based on the region information included in the additional data acquired from each of the plurality of image sensors, wherein the region information includes a part of or all of identification information of the region, information indicating a position of the region, and information indicating a size of the region.

A method for local automatic white balance (AWB) of wide dynamic range (WDR) images is provided that includes collecting statistics for local AWB by an image signal processor (ISP) from a first WDR image generated by the ISP, receiving, by the ISP, a plurality of local gain lookup tables (LUTs), one for each color channel, wherein the plurality of local gain LUTs is generated using the statistics, and applying, by the ISP, a gain value to each pixel in a second WDR image generated by the ISP, wherein the gain value for the pixel is determined by the ISP using the local gain LUT for the color channel of the pixel.

A method for local automatic white balance (AWB) of wide dynamic range (WDR) images is provided that includes collecting statistics for local AWB by an image signal processor (ISP) from a first WDR image generated by the ISP, receiving, by the ISP, a plurality of local gain lookup tables (LUTs), one for each color channel, wherein the plurality of local gain LUTs is generated using the statistics, and applying, by the ISP, a gain value to each pixel in a second WDR image generated by the ISP, wherein the gain value for the pixel is determined by the ISP using the local gain LUT for the color channel of the pixel.