Korea Advanced Institute of Science and Technology

Samsung Electronics Co., Ltd.

Hyundai Motor Company

Kia Motors Corporation

Samsung Sds Co., Ltd.

Postech Research and Business Development Foundation

Kia Motor Corporation

Jae Seok Choi

Mun Churl Kim

Yong Woo Kim

Hyong Euk Lee

Kinam Kwon

MunChurl Kim

Byung In Yoo

Sangwon Lee

Sujin Lee

Jongmin Lee

Ki Seok Lee

Youngsu Moon

Cheon An Lee

Hyunseung Lee

Sanghyun Kim

Yongwoo Kim

Yong Hoon Kim

Yang Geol Lee

Eunhee Kang

Byoung Soo Lee

Cheon Lee

Minsu Cho

Nam Soo Jeon

Min Jeong Lyu

Hyun Woo Jung

Geonseok Seo

Ji Joong Gil

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.

Method and apparatus for image restoration based on burst image

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.

Method and apparatus with noise consideration

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.

Image processing method and device using feature map compression

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.

Image pipeline processing method and device

Method and device of super resolution using feature map compression

Image processing method and device using a line-wise operation

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.

Image enhancement method, image enhancement apparatus, and method and apparatus for training image enhancement apparatus

An image processing method and apparatus using a line unit operation is disclosed. The image processing apparatus includes a receiver configured to receive an image, at least one first line buffer configured to output the received image to be an image line of a line unit, a first convolution operator configured to generate a feature map by performing a convolution operation based on the output image line, and a feature map processor configured to store the generated feature map as at least one line unit and process the feature map stored as the line unit to be output in a two-dimensional (2D) or higher dimensional form.

Super-resolution method and device using linewise operation

An image processing apparatus obtains a first output image by applying an image to a first training network model, obtains a second output image by applying the image to a second training network model, and obtains a reconstructed image based on the first output image and the second output image. The first training network model is a model that uses a fixed parameter obtained through training of a plurality of sample images, the second training network model is trained to minimize a difference between a target image corresponding to the image and the reconstructed image.

Image processing apparatus and image processing method thereof

An exhaust gas recirculation (EGR) cooler is provided and includes a plurality of tubes that are spaced apart from each other and a cavity that is disposed on an engine to receive the plurality of tubes. A coolant guide guides a coolant to the plurality of tubes and a cover then closes the cavity. The cavity has an inlet port that communicates with a water jacket of the engine and the cavity receives the coolant from the water jacket of the engine through the inlet port.

Exhaust gas recirculation cooler

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 two-dimensional pixel information; at least one first line buffer for outputting the two-dimensional pixel information into a line-wise data line; an operator for performing a convolution operation on the basis of the data line data; and at least one second line buffer for outputting the data line on which the operation has been performed.

Image processing method and device using line input and output

An image conversion method includes: dividing a low-resolution image to generate a plurality of low-resolution image patches having N (N being a natural number of 2 or greater) number of pixels; classifying the low-resolution image patches into a plurality of image categories; converting the low-resolution image patches by using a conversion kernel for each image patch corresponding to its image category among prestored conversion matrices, to generate high-resolution image patches having L (L being a natural number) number of pixels, which is less than the N number of pixels; and arranging the high-resolution image patches to generate a high-resolution image. According to the image conversion method, an operation amount can be reduced compared with a conventional technique, and thus the image conversion method can be implemented in hardware having low complexity. A high quality and high-resolution image can be generated regardless of characteristic information of an image signal.

Method of converting low-resolution image to high-resolution image and image conversion device performing method

Provided is an apparatus for executing an update, which executes an update of a specific application installed in a device, the apparatus including: a predetermined value receiving unit configured to receive information on a randomly selected value among values within a predetermined range from an update providing server; an open date receiving unit configured to receive information on an update open time from the update providing server; an update time calculating unit configured to calculate an update time of the specific application by using the received information on the randomly selected value and on the update open time; an update information receiving unit configured to receive update information about the specific application after the calculated update time; and an update executing unit configured to execute an update of the specific application by using the received update information.

Apparatus and method of executing update, recording medium using the same, and server and method of providing update

A multi-connector, and a charging cable and a data cable including the same are disclosed. The multi-connector includes a 24-pin connector and a 20-pin connector that may be used regardless of the type and manufacturer of a portable terminal. The multi-connector includes a first connector body having a first connector installed on a side thereof, a second connector body having a second connector installed on a side thereof, and a hinge shaft to connect the first connector body to the second connector body. The first connector body and/or the second connector body are pivotable about the hinge shaft.

Multi-connector, and charging cable and data cable having the same

An intake system of an engine for a vehicle, may include a surge tank including a first flange, and an intake manifold including a second flange connected with the first flange of the surge tank, wherein the intake manifold may include a main body including a fuel rail and intake ports corresponding to cylinders, and a guide member provided on the main body to guide the surge tank coupled with the main body in a direction where the surge tank becomes separated and more distant from the fuel rail of the intake manifold when a vehicle collision occurs.

Growing community of inventors

Daejeon, South Korea

Jae Seok Choi