Abstract: Systems and methods for super-resolution (SR) are described. The SR method includes determining a direction type of an input image based on a gradient of the input image, obtaining a first intermediate image based on the direction type using a look-up table (LUT) that stores an SR operation result of a pixel value combination corresponding to a kernel set mapped to the determined direction type, wherein the first intermediate image is an SR image corresponding to the input image, applying SR interpolation to the input image to obtain a baseline image, and obtaining an output image based on the first intermediate image and the baseline image.

Abstract: A neural network-based image processing method and apparatus are provided. A method includes receiving input image data comprising original image data, when a current image processing mode is an independent processing mode, generating first intermediate image data by executing a main neural network based on the original image data and by not executing an auxiliary neural network based on the original image data, when the current image processing mode is in a cooperative processing mode, generating second intermediate image data by determining an auxiliary parameter by executing the auxiliary neural network based on the original image data and by executing the main neural network based on the original image data and based on the auxiliary parameter, and generating output image data by operating an image signal processing (ISP) block based the first intermediate image data or the second intermediate image data according to the current image processing mode.

Abstract: A processor-implemented method includes: obtaining a plurality of image frames acquired for a scene within a predetermined time; determining loss values respectively corresponding to the plurality of image frames; determining a reference frame among the plurality of image frames based on the loss values; and generating a final image of the scene based on the reference frame.

Abstract: An image restoration method and apparatus are provided. The image restoration method includes determining auxiliary data corresponding to a plurality of filter kernels by filtering target data with the plurality of filter kernels, determining new input data by combining the auxiliary data with at least some input data of layers of a neural network-based image restoration model, generating, based on the new input data, a restored image of the input image by executing the neural network-based image restoration model, wherein the filter kernels are not part of the neural network-based image restoration model.

Abstract: A device with image acquisition includes: a first phase mask disposed at a front end of a display layer and configured to modulate external light; the display layer comprising pixel areas between hole areas through which the modulated light that has passed through the first phase mask passes; a second phase mask disposed at a rear end of the display layer and configured to modulate the modulated light that has passed through the first phase mask; an image sensor disposed at a rear end of the second phase mask and configured to generate a raw image by sensing the modulated light that has passed through the second phase mask; and a processor configured to perform image processing on the raw image, based on blur information corresponding to the raw image.

Abstract: An image acquisition apparatus includes a display layer including hole regions through which external light is received and pixel regions arranged between the hole regions, an image sensor disposed under the display layer and configured to generate a raw image by sensing the external light received through the hole regions, and a processor configured to perform image processing on the raw image based on blur information based on an arrangement of the hole regions.

Abstract: A method with image augmentation includes recognizing, based on a gaze of the user corresponding to the input image, any one or any combination of any two or more of an object of interest of a user, a situation of the object of interest, and a task of the user from partial regions of an input image determining relevant information indicating an intention of the user, based on any two or any other combination of the object of interest of the user, the situation of the object of interest, and the task of the user, and generating a visually augmented image by visually augmenting the input image based on the relevant information.

Abstract: A method and apparatus for image restoration based on burst images. The method includes generating a plurality of feature representations corresponding to individual images of a burst image set by encoding the individual images, determining a reference feature representation from among the plurality of feature representations, determining a first comparison pair including the reference feature representation and a first feature representation of the plurality of feature representations, generating a first motion-embedding feature representation of the first comparison pair based on a similarity score map of the reference feature representation and the first feature representation, generating a fusion result by fusing a plurality of motion-embedding feature representations including the first motion-embedding feature representation, and generating at least one restored image by decoding the fusion result.

Abstract: 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.

Abstract: A method includes: generating, based on a student network result of an implemented student network provided with an input, a sample corresponding to a distribution of an energy-based model based on the student network result and a teacher network result of an implemented teacher network provided with the input; training model parameters of the energy-based model to decrease a value of the energy-based model, based on the teacher network result and the student network result; and training the implemented student network to increase the value of the energy-based model, based on the sample and the student network result.

Abstract: A method and apparatus with noise consideration are provided. The method includes generating, using a noise model, a non-normal noise map corresponding to a noise of an input image, and generating an enhanced image of the input image by implementing an image enhancement model based on the input image and the non-normal noise map, where the noise of the input image follows a non-normal distribution.

Abstract: A computing device and an operation method thereof are disclosed. The method includes unshuffling first image data to generate input data, generating output data by implementing a neural network (NN) model provided the input data, and generating second image data by shuffling the output data.

Abstract: A method with image processing includes: setting an offset window for an offset pattern of a kernel offset and an offset parameter for an application intensity of the kernel offset; determining an output kernel by applying the kernel offset to an input kernel based on the offset window and the offset parameter; and adjusting contrast of a degraded image using the output kernel.

Abstract: A processor-implemented method with degraded image restoration includes: receiving a degraded training image; training a first teacher network of an image restoration network and a second teacher network of the image restoration network to infer differential images corresponding to the degraded training image, wherein each of the first teacher network and the second teacher network comprises a differentiable activation layer and a performance of the first teacher network is greater than that of the second teacher network; initially setting a student network of the image restoration network based on the second teacher network; and training the student network to infer a differential image corresponding to the degraded training image by iteratively backpropagating, to the student network, a contrastive loss that decreases a first difference between a third output of the student network and a first output of the first teacher network and increases a second difference between the third output and a second output

Abstract: An image enhancement method, an image enhancement apparatus, and a method and apparatus for training the image enhancement apparatus are provided. The image enhancement apparatus may enhance a quality of a raw image captured by an under-display camera (UDC). The image enhancement apparatus may process the raw image for each channel according to characteristics of a photographing environment of the UDC. The image enhancement apparatus may further enhance the image by processing the raw image to reflect characteristics for each channel.

Abstract: Methods and apparatuses with training or image enhancement are disclosed. The image enhancement method includes obtaining an input image, estimating a noise distribution of the input image by implementing a noise model based on the input image, and generating an enhanced image by implementing an image enhancement model dependent on the input image and the estimated noise distribution.

Abstract: A method and apparatus with image correction is provided. A processor-implemented method includes generating, using a neural network model provided an input image, an illumination map including illumination values dependent on respective color casts by one or more illuminants individually affecting each pixel of the input image, and generating a white-adjusted image by removing at least a portion of the color casts from the input image using the generated illumination map.

Abstract: Provided are methods and apparatuses for determining a target object in an image based on an interactive input. A target object determining method acquires first feature information corresponding to an image and second feature information corresponding to an interactive input; and determines a target object corresponding to the interactive input from among objects in the image based on the first feature information and the second feature information.

Abstract: A method with image augmentation includes recognizing, based on a gaze of the user corresponding to the input image, any one or any combination of any two or more of an object of interest of a user, a situation of the object of interest, and a task of the user from partial regions of an input image determining relevant information indicating an intention of the user, based on any two or any other combination of the object of interest of the user, the situation of the object of interest, and the task of the user, and generating a visually augmented image by visually augmenting the input image based on the relevant information.

Abstract: A modeling method searches for a sequence matched to a user input using a fluid animation graph generated based on similarities among frames included in sequences included in the fluid animation graph and models a movement corresponding to the user input based on a result of the searching. Provided also is a corresponding apparatus and a method for preprocessing for such modeling.