Abstract: A method and device for image enhancement based on blur segmentation are provided. The method of image enhancement includes: generating a blur segmentation map including indications of blur characteristics of respective pixels of a blur image, wherein the blur characteristics are in predetermined blur characteristic categories, and wherein the generating is performed by classifying the blur characteristic of each pixel of the blur image into one of the predetermined blur characteristic categories; converting the blur segmentation map into an image residual error corresponding to a blur component of the blur image; and generating the deblurred image based on the blur image and the image residual error.

Abstract: A method of generating compensation data for a display device is disclosed that includes measuring a front luminance and a side luminance of the display device, generating a front correction value and a side correction value based on the front luminance and the side luminance, respectively, determining a front background component of the front correction value and a side background component of the side correction value, generating a front background-synthesized side correction value by replacing the side background component with the front background component in the side correction value, and generating the compensation data based on the front correction value and the front background-synthesized side correction value.

Abstract: A method and apparatus for image restoration using burst images are provided, where the method includes receiving a burst image set including image frames, determining shifted data representing a shift level of each of the image frames using a shift estimation model, selecting a base image from the image frames based on the shifted data, and performing image restoration by synthesizing at least a portion of the image frames based on the base image.

Abstract: An image processing method includes computing a blur kernel of an input image using a kernel estimation model, performing kernel-based deblurring on the input image using the blur kernel to obtain a deconvolved image, and generating an output image by performing kernel-free deblurring based on the deconvolved image.

Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the image; and a compressor for compressing the feature map into units of at least one line; and a decompressor for reconstructing the feature map compressed into units of lines.

Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; at least one first line buffer for outputting the image into a line-wise image line; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the output from the first line buffer; and a feature map processor for storing the output from the first convolution operator in units of at least one line, and processing so as to output the feature map stored in units of at least one line into a two-dimensional form, wherein at least one convolution operation operates in the form of a pipeline.

Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the image; and a compressor for compressing the feature map into units of at least one line; and a decompressor for reconstructing the feature map compressed into units of lines.

Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; at least one first line buffer for outputting the image into a line-wise image line; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the output from the first line buffer; and a feature map processor for storing the output from the first convolution operator in units of at least one line, and processing so as to output the feature map stored in units of at least one line into a two-dimensional form, wherein at least one convolution operation operates in the form of a pipeline.

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: The present invention relates to coronavirus infectious disease COVID-19 therapeutic proteins CTP alpha, CTP beta, CTP gamma, CTP delta, and uses thereof. Compared to a known peptide (P6) which mimics the binding site of a receptor binding domain (RBD) of SARS-CoV and angiotensin-converting enzyme 2 (ACE2), the therapeutic proteins CTP alpha, CTP beta, CTP gamma, and CTP delta according to the present invention comprise a novel part obtained by adding a novel sequence of amino acids, wherein the interaction of atoms constituting the amino acids has been fundamentally designed in order to strengthen the binding of SARS-CoV2 to a novel epitope of RBD.

Abstract: The present invention relates to a peptide for treatment of the corona virus infection COVID-19 and a use thereof. In order to make the binding to the new epitope of SARS-CoV2 RBD stronger compared to the peptide (P6) simulating the conventionally known binding site between SARS-CoV RBD and ACE2, the peptide of the present invention includes a new portion added with a novel amino acid sequence fundamentally designed for interaction in the dimension of atoms consisting of the amino acids. Suggested in the present invention is a novel design of a peptide having higher binding affinity than conventionally known peptides, wherein an expanded peptide is creatively designed to additionally interact with charged amino acids of D420 and K458, located at the rear side of the known binding boundary between RBD and hACE2. The peptide of the present invention exhibits high possibility as a therapeutic agent for COVID-19.

Abstract: An optical compensation method includes displaying a first image in a display device, the first image including a dot pattern obtained by allowing target pixels spaced apart from each other emit light, at least two other pixels being disposed between the target pixels; generating first image capture data by capturing the first image displayed in the display device through an image capture device; displaying a second image in the display device; generating second image capture data by capturing the second image displayed in the display device through the image capture device; generating deblurring data by deblurring the second image capture data, based on the first image capture data; generating compensation data for luminance correction of the display device, based on the deblurring data; and storing the compensation data in a memory device.

Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; at least one first line buffer for outputting the image into a line-wise image line; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the output from the first line buffer; and a feature map processor for storing the output from the first convolution operator in units of at least one line, and processing so as to output the feature map stored in units of at least one line into a two-dimensional form, wherein at least one convolution operation operates in the form of a pipeline.

Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the image; and a compressor for compressing the feature map into units of at least one line; and a decompressor for reconstructing the feature map compressed into units of lines.

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 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 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: Provided is a spot detection device including an imager configured to capture a display panel displaying a first image of a first grayscale and a second image of a second grayscale different from the first grayscale and generate image data, and a spot detector configured to receive the image data from the imager in order to detect a spot. The image data includes first image data obtained by capturing the first image, second image data obtained by capturing the second image, and a plurality of third image data obtained by capturing portions of the first image.