Samsung Electronics Co., Ltd.

Snu Rdb Foundation

Deokyoung Kang

Yang Ho Cho

Dong Kyung Nam

Daekun Yoon

Kyuhwan Choi

Geonwoo Kim

Seho Lee

Sung Kwang Cho

Myung Joo Kang

Seung Won Jeong

Jin Je Park

An apparatus with image processing includes: one or more processors configured to: generate a full sampling image by demosaicing a first color filter array (CFA)-based input image; based on a trained color conversion model trained for color conversion and noise suppression of the full sampling image, determine a bias and a conversion matrix corresponding to each pixel of the full sampling image; and based on the conversion matrix and the bias, convert a color space of the full sample image, corresponding to the first CFA, into a color space corresponding to a second CFA.

Apparatus and method with image processing

An image processing method and apparatus are provided. The image processing method includes converting an input image to a first channel separated image having a same resolution as the input image, the first channel separated image comprising a plurality of separate channels, generating a second channel separated image by performing a convolution operation on the first channel separated image, the second channel separated image comprising the plurality of separate channels and having a same resolution as the first channel separated image, and generating a restored image corresponding to the input image based on the second channel separated image.

Image processing method and apparatus

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.

Imaging device and method

An image restoration method and apparatus are provided. The image restoration method includes acquiring a target image, and acquiring a restoration image of the target image from an image restoration model to which the target image and pixel position information of the target image are input.

Method and apparatus for restoring image

A method of driving a lens array camera may include simultaneously driving a first group of sensing elements from among a plurality of sensing elements, each sensing element from among the first group of sensing elements corresponding to a same original signal viewpoint, wherein the plurality of sensing elements is included in a sensor corresponding to the lens array camera including N rows of N lenses, N being a natural number.

Lens array camera and method of driving lens array camera

A method for processing an image by using a neural network is provided. The method includes obtaining a target image; and obtaining a restored image corresponding to the target image by using the neural network, the neural network including a plurality of residual blocks connected sequentially. The obtaining the restored image includes obtaining the restored image by performing, in each residual block of the plurality of residual blocks, image processing on an input image, which is input from a previous residual block, on different scales, and providing results of the image processing performed on the different scales to a subsequent residual block.

Method and apparatus for restoring an image by using a neural network including multi-scale residual blocks

An image restoration apparatus generates a plurality of warped images by warping each of a plurality of input images based on respective depths corresponding to a plurality of disparities, and generates an output image with a high resolution based on the plurality of input images and the plurality of warped images using an image restoration model.

Provided is an image restoration apparatus and method. The image restoration apparatus may store an image restoration model including a convolutional layer corresponding to kernels having various dilation gaps, and may restore an output image from a target image obtained by rearranging a compound eye vision (CEV) image by the image restoration model.

An imaging device may code light, passing through an imaging optical lens arranged in a multi-lens array (MLA), and may transmit the light to a sensing element, and the sensing element may restore an image based on sensed information.

Image sensor

Provided is an operation method of an image sensor including a plurality of pixels, the operation method including transmitting a first output voltage of a first pixel to a first amplifier, transmitting the first output voltage to a second amplifier by controlling a first switch connected to the first pixel, transmitting a second output voltage of a second pixel to be binned with the first pixel to the second amplifier by controlling a second switch connected to the second pixel, and outputting selectively one of a first output of the first amplifier and a second output of the second amplifier based on an illuminance of an environment in which the image sensor operates.

Image sensor and operation method of the same

An aberration correction method and apparatus. The apparatus includes at least one processor, and an input/output unit configured to receive an captured image, wherein the processor is configured to initialize a first matrix or a second matrix by reducing a matrix of a point spread function (PSF) of a lens included in a capturing device used to capture the captured image, iteratively perform an aberration removal and a noise removal based on the captured image and the first matrix or the second matrix, and output a final original image as a result of the iteratively performing. Here, the first matrix is a matrix obtained by reducing the number of indices indicating light arrival points of the matrix of the PSF, and the second matrix is a matrix obtained by reducing the number of indices corresponding to light arrival points of a transposed matrix of the PSF.

Method and apparatus for correction of aberration

An image sensor and an image sensing method are provided. The image sensor may restore a high resolution image with respect to a high magnification based on sensing information corresponding to different fields of view (FOVs) and that is received through lens elements having a same focal length and different lens sizes.

Image sensor and image sensing method

Provided is a method and apparatus for restoring an image, the apparatus including a plurality of lenses configured to pass a plurality of rays, a sensor including a target sensing element configured to receive a target ray passing a first lens among the plurality of lenses, and a second sensing element configured to receive a second ray passing a second lens among the plurality of lenses, the first lens being different from the second lens, and a processor configured to determine the second sensing element based on a difference between a direction of the target ray and a direction of the second ray, and to restore color information corresponding to the target sensing element based on color information detected by the second sensing element.

Growing community of inventors

Suwon-si, South Korea

Deokyoung Kang