Abstract: An apparatus and method for processing an image are disclosed. The method includes: segmenting both a first image and a second image and generating segmentation mask pairs, each segmentation mask pair having a segmentation mask of the first image and a segmentation mask of the second image; generating local homography matrices of the first image with respect to the second image, based on the segmentation mask pairs, the first image, and the second image; and generating a synthetic image obtained by aligning the first image with the second image, wherein the aligning is performed based on the local homography matrices, the segmentation mask pairs, the first image, and the second image.

Abstract: An image restoration device obtains input data including input image information for each viewpoint, and generates an output image from warped image information generated by warping the input image information using a global transformation information of each viewpoint and disparity information of each viewpoint, using an image restoration model.

Abstract: A method and an electronic device with image registration are provided. The method includes generating a first optical flow between a first partial image and a second partial image, which are captured by respective first and second cameras using an optical flow estimation model; generating disparity information between the first partial image and a third partial image, captured by a third camera, based on depth information of the first partial image generated using the first optical flow; and estimating a second optical flow between the first partial image and the third partial image based on the generated disparity information for generating a registration image.

Abstract: A method with image processing includes: receiving an input image including Bayer images captured by a plurality of lenses included in a lens assembly; generating channel separation images by separating each of the Bayer images by a plurality of channels; determining corresponding points such that pixels in the channel separation images are displayed at the same position on a projection plane, for each of the plurality of lenses; performing binning on the channel separation images, based on a brightness difference and a distance difference between a target corresponding point and a center of a pixel including the target corresponding point, corresponding to each of the corresponding points in channel separation images that correspond to a same channel and that are combined into one image, for each of the plurality of lenses; restoring the input image for each of the plurality of lenses based on binned images generated by performing the binning; and outputting the restored input image.

Abstract: Provided are an image processing method and an image processing device. The image processing method includes generating an image based on viewpoint information of a user; rendering the image based on information about what is in front of the user; and outputting the rendered image using an optical element.

Abstract: The present invention relates to a heteroaryl derivative compound and a use thereof. The heteroaryl derivative of the present invention exhibits excellent inhibitory activity against HER2 and EGFR, and thus can be effectively used as a therapeutic agent for HER2- and/or EGFR-associated diseases.

Abstract: An image sensor includes a color filter array including a first color filter including a first number of blue pass filtering elements, the first number of red pass filtering elements, and green pass filtering elements in a first pattern, wherein a number of the green pass filtering elements in the first pattern is twice the first number, and a second color filter including a second number of blue pass filtering elements, the second number of red pass filtering elements, and green pass filtering elements in a second pattern, wherein a number of green pass filtering elements in the second pattern is twice the second number, and the second number is greater than the first number. The second color filter may surround an area of the first color filter.

Abstract: An electronic device includes an image sensor including a color filter having a plurality of color channels, a memory storing a plurality of color conversion matrices and instructions, and a processor. The processor is configured to obtain noise information of a color image captured by the image sensor, select a target matrix from among the plurality of the color conversion matrices based on the obtained noise information, and generate a color converted image by applying the selected target matrix to the color image.

Abstract: Provided is an image processing method of an image processing model, the image processing method including obtaining an input image group, the input image group including a plurality of low-resolution images corresponding to a plurality of different viewpoints, respectively, obtaining a feature of low-resolution images by extracting a feature for each low-resolution image of the plurality of low-resolution images included in the input image group, obtaining a fusion residual feature by fusing the feature of low-resolution images, and obtaining a super-resolution image corresponding to the input image group based on the fusion residual feature.

Abstract: An image processing method includes: based on an imaging device generating an input array image of a multi-view through an array lens, determining a first setting parameter indicating whether to use the multi-view or a single view selected from the multi-view; determining a second setting parameter indicating whether a priority is assigned to sensitivity enhancement based on pixel binning or to resolution enhancement based on pixel interpolation; determining an image processing mode based on the first setting parameter and the second setting parameter; and generating an output image by performing image processing on the input array image based on a processing procedure that is based on the determined image processing mode.

Abstract: An image processing method for demosaicing with reduced moire includes selecting, with respect to a target channel among a plurality of color channels for an input image, a target pixel unassigned with a color value for the target channel, calculating, with respect to the target pixel, gradient values respectively corresponding to a first direction and a second direction associated with the target channel, calculating, with respect to the target pixel, moire values respectively corresponding to the first direction and the second direction, and determining an interpolation direction of the target pixel for the target channel to be one of the first direction and the second direction, based on the calculated gradient values and the calculated moire values.

Abstract: An eye reconstruction-based eye tracking method and apparatus are provided. The eye tracking method includes generating a reconstructed image by performing eye reconstruction with respect to an input image, determining a difference value between the input image and the reconstructed image, selecting one of the input image, the reconstructed image, and a replacement image as a target image based on the determined difference value, and performing eye tracking based on the target image.

Abstract: Disclosed is a color transform method performed by an electronic device that includes generating an initial color transformed image by performing color transform on a raw image, determine noise amplification degrees indicating degrees to which noise included in the raw image is amplified by the color transform, processing the determined noise amplification degrees, and generating a final color transformed image by filtering the generated initial color transformed image using the processed noise amplification degrees and at least one of the raw image or luminance information of the raw image.

Abstract: An imaging device is provided. The imaging device may sense light passing through a corresponding imaging lens and a corresponding color filter in sensing elements disposed in a sensing region for each color channel, and generate sensing data based on a grouping of color intensity values sensed by the sensing elements for each sensing region based on a binning size determined based on an illuminance of light.

Abstract: A method of estimating an optical flow includes processing, using an image processing pass, a first image and a second image separately, and estimating the optical flow based on a second image attention feature map of the first image and a second image attention feature map of the second image. The processing using the image processing pass includes extracting a feature map by encoding an image, outputting a first image fusion attention feature map by fusing row relationship information of the image with the image feature map, outputting a first image attention feature map of the image based on the first image fusion attention feature map and the image feature map, outputting a second image fusion attention feature map by fusing column relationship information of the image with the first image attention feature map, and generating a second image attention feature map of the image based on the second image fusion attention feature map and the first image attention feature map.

Abstract: An image sensor includes a color filter array including a first color filter including a first number of blue pass filtering elements, the first number of red pass filtering elements, and green pass filtering elements in a first pattern, wherein a number of the green pass filtering elements in the first pattern is twice the first number, and a second color filter including a second number of blue pass filtering elements, the second number of red pass filtering elements, and green pass filtering elements in a second pattern, wherein a number of green pass filtering elements in the second pattern is twice the second number, and the second number is greater than the first number. The second color filter may surround an area of the first color filter.

Abstract: A method of learning a parameter of a sensor filter and an apparatus for performing the method are provided. The learning method may include performing a simulation on a target image for each spectrum of a sensor filter, obtaining an output value by inputting the simulated image to a vision model for a vision task, and learning a parameter of the sensor filter based on a loss between a label of the vision model and the output value of the vision model.

Abstract: An imaging device includes an imaging lens array including a plurality of imaging lenses each with a same focal length, the plurality of imaging lenses being configured to capture a scene; a sensing array comprising a plurality of sensors configured to receive light passing through the plurality of imaging lenses; a processor configured to determine a scene depth plane corresponding to the scene based on a comparison, for each of a plurality of candidate depths, between reference pixel values based on first sensors of the plurality of sensors corresponding to a reference imaging lens of the plurality of imaging lenses and target pixel values that are based on second sensors of the plurality of sensors corresponding to a target imaging lens of the plurality of image lenses; and a lens driver configured to position the imaging lens array to be disposed at a point corresponding to the scene depth plane.

Abstract: A method and apparatus for array image processing are provided. The method includes receiving sub images corresponding to different views of an input array image generated through an array lens, generating temporary restored images based on the sub images using a gradient between neighboring pixels of each of the sub images, determining matching information based on a view difference between pixels of the sub images using a neural network model, based on a pixel distance between matching pairs of the pixels of the sub images using the matching information, extracting refinement targets from the matching pairs, refining the matching information by replacing at least some of target pixels included in the refinement targets based on a local search of a region based on pixel locations of the refinement targets, and generating an output image of a single view by merging the temporary restored images based on the refined matching information.

Abstract: An optimization method includes determining first information related to a difference between the color filter spectrum and the color spectrum or a difference between an image transformed by the color transformation matrix and a ground truth (GT) image in the reset color space, determining second information representing smoothness of the color filter spectrum, third information representing a transmittance of the color filter spectrum, calculating a cost value based on the first information, the second information, and the third information, compare the calculated cost value and a threshold, and updating one of the filter spectrum information and the color transformation matrix in response to the calculated cost value being equal to or greater than the threshold.