Abstract:
A method and apparatus for processing a multi-view image are provided. A priority may be assigned to each hole pixel in a hole region generated when an output view is generated. The priority of each hole pixel may be generated by combining a structure priority, a confidence priority, and a disparity priority. Hole rendering may be applied to a target patch including a hole pixel having a highest priority. The hole pixel may be restored by searching for a source patch most similar to a background of the target patch, and copying a pixel in the found source patch into a hole pixel of the target patch.
Abstract:
An apparatus having a lens assembly array and a method of using the apparatus are provided. The apparatus includes a lens assembly array including a plurality of lens assemblies each including a plurality of individual lenses in a form of an array, an actuator assembly configured to move at least a portion of the plurality of lens assemblies in at least one direction, and a single image sensor configured to generate image data including a plurality of sub-images corresponding to the plurality of lens assemblies based on light passing through the lens assembly array.
Abstract:
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.
Abstract:
Provided is an imaging device including a sensing array including a plurality of sensing elements, an imaging lens array including a plurality of imaging optical lenses, each of the plurality of imaging optical lenses having a non-circular cross-section perpendicular to an optical axis, and configured to transmit light received from an outside of the imaging device, and a condensing lens array including a plurality of condensing lenses disposed between the imaging lens array and the sensing array, and configured to transmit the light passing through the imaging lens array to the sensing elements, wherein a number of the plurality of imaging optical lenses is less than a number of the plurality of condensing lenses.
Abstract:
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.
Abstract:
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.
Abstract:
An image sensor and a method of manufacturing the image sensor are provided. The image sensor includes a block layer including an absorption layer and a transparent layer, a lens element located below the block layer, and a sensing element located to face the lens element.
Abstract:
A multi-lens based capturing apparatus and method are provided. The capturing apparatus includes a lens array including lenses and a sensor including sensing pixels, wherein at least a portion of sensing pixels in the sensor may generate sensing information based on light entering through different lenses in the lens array, and light incident on each sensing pixel, among the portion of the plurality of sensing pixels may correspond to different combinations of viewpoints.
Abstract:
A method of processing an image includes obtaining a position of a viewpoint corresponding to the image, selecting, based on the position, two reference rays closest to a ray included in the image from among a plurality of reference rays included in reference images photographed in advance from different reference viewpoints; determining whether a difference between color values of the selected reference rays is less than or equal to a threshold; and determining a color value of the ray based on the color values of the selected reference rays in response to the difference between the color values of the selected reference rays being determined to be less than or equal to the threshold.
Abstract:
A displaying device and a displaying method are provided. The displaying device may include a light source configured to emit a plurality of input rays, a spatial light modulator configured to adjust at least one from among a brightness and a color of each of the input rays, and a tilting mirror array configured to adjust a progress direction of each of the input rays of which at least one from among the brightness and the color is adjusted and to output the input rays based on the adjusted progress direction.