Abstract: Provided is a blur processing method and apparatus that may determine whether a blur occurs in an image generated by a Time of Flight (ToF) camera, and may deblur a blur using a value of a normal adjacent pixel in which the blur is absent when the blur occurs.

Abstract: An apparatus and method for predicting an eye position includes a storer configured to store detected position information of an eye of user during a sample time interval, a calculator configured to calculate a weighted average value of a variation of the detected position information, and a predictor configured to generate prediction position information of the eye of user at a target time based on the weighted average value, and the calculator is configured to apply a weight to the variation of the detected position information such that the weight increases as the target time is approached during the sample time interval.

Abstract: Provided is a depth image generating apparatus and method. The light-receiving unit may include a first gate and a second gate and a depth calculator to calculate a depth based on first light information through fourth light information. The first gate may obtain the first light information from a reflected light of a light emitted based on a first pulse and the second gate may obtain the second light information from a reflected light of a light emitted based on a second pulse, and then the first gate may obtain the third light information from a reflected light of a light emitted based on a third pulse and the second gate may obtain the fourth light information from a reflected light of a light emitted based on a fourth pulse.

Abstract: A method for generating a three-dimensional (3D) image may detect a current eye position of a user and render a 3D image based on at least one of a previously detected eye position of the user and previously generated stereo images. A cycle at which the current eye position of user is detected and a cycle at which a 3D image is rendered may be asynchronous.

Abstract: A method and apparatus for processing a depth image that removes noise of a depth image may include a noise estimating unit to estimate noise of a depth image using an amplitude image, a super-pixel generating unit to generate a planar super-pixel based on depth information of the depth image and the noise estimated, and a noise removing unit to remove noise of the depth image using depth information of the depth image and depth information of the super-pixel.

Abstract: An image processing apparatus may include a sensor unit which generates both a color image and a depth image. A color-depth time difference correcting unit may correct a mismatching that occurs due to a time difference between a point in time when the color image is generated and a point in time when the depth image is generated. An image generator may generate a stereoscopic image or a multi-view image using the color image and the depth image after the mismatching is corrected.

Abstract: An eye tracking apparatus is operable in both first and second illumination environments where the second illumination is associated with a higher illumination environment than the first illumination. The apparatus includes an image capturer configured to capture an image of a user, an image processor configured to detect an eyepoint of the user in the captured image, and an optical source configured to emit infrared light to the user in a first illumination mode. The image capturer includes a dual bandpass filter configured to allow infrared light and visible light to pass.

Abstract: An image processing apparatus and method are provided. A control unit may divide input image array data into a plurality of sub-blocks, and a first arithmetic logic unit (ALU) may generate an integral image of at least one of the plurality of sub-blocks. The control unit may determine each of the plurality of sub-blocks to be included in any one of a first sub-block group and a second sub-block group, store the integral image of each sub-block included in the first sub-block group on the first memory, and store the integral image of each sub-block included in the second sub-block group on the second memory.

Abstract: An apparatus for generating an image representing an object is provided. The apparatus may include a filtering unit configured to acquire first light of a first wavelength band and second light of a second wavelength band, which are included in light reflected from the object, by using a single filter; a sensing unit configured to convert both the first light and the second light into charges or convert only the second light into charges; a first image generating unit configured to generate a first image representing the object by correcting color values corresponding to the charges into which the first light and the second light have been converted; and a second image generating unit configured to generate a second image representing the object by using the charges into which the second light has been converted.

Abstract: An image processing apparatus is provided. A silhouette extractor may extract a silhouette image of a target object from an input depth image. A first calculator may determine a location of at least one limb of the target object and a location of at least one joint connecting the at least one limb by applying a rectangle fitting algorithm with respect to the silhouette image.

Abstract: A depth noise filtering method and apparatus is provided. The depth noise filtering method may perform spatial filtering or temporal filtering according to depth information. In order to perform spatial filtering, the depth noise filtering method may determine a characteristic of a spatial filter based on depth information. Also, in order to perform temporal filtering, the depth noise filtering method may determine a number of reference frames based on depth information. The depth noise filtering method may adaptively remove depth noise according to depth information and thereby enhance a noise filtering performance.

Abstract: Provided is an image processing apparatus, medium, and method. The image processing apparatus may include a first calculator and a second calculator. The first calculator may calculate a first weight of a first frame depth value of a first pixel of a depth image and a second weight of a second frame depth value of the first pixel, based on an obtainment time difference between the first frame depth value of the first pixel and the second frame depth value of the first pixel among a plurality of frame depth values of the first pixel. The second calculator may determine a corrected first frame depth value of the first pixel using a linear sum that is calculated by applying the first weight to the first frame depth value of the first pixel, and by applying the second weight to the second frame depth value of the first pixel.

Abstract: Provided is an image processing apparatus. The image processing apparatus may extract a three-dimensional (3D) silhouette image in an input color image and/or an input depth image. Motion capturing may be performed using the 3D silhouette image and 3D body modeling may be performed.

Abstract: An image processing method and apparatus includes selecting a first pixel group including at least one pixel from an input color image; selecting a second pixel group including at least one pixel corresponding to each of the at least one pixel included in the first pixel group from an input depth image; calculating a transformation function of the first pixel group and second pixel group based on a coordinate value of each of the at least one pixel included in the first pixel group and a coordinate value of each of the at least one pixel included in the second pixel group; and matching each pixel of the input color image with each pixel of the input depth image based on the transformation function.

Abstract: An image processing apparatus is provided. The image processing apparatus determines whether a first charge quantity of charges stored in a first charge storage is greater than or equal to a predetermined saturation level, the first charge storage among a plurality of charge storages configured to store charges generated by a sensor of a depth camera. According to the determination result, when the first charge quantity is greater than or equal to the saturation level, the image processing apparatus may calculate the first charge quantity from at least one second charge quantity of charges stored in at least one second charge storage which is different from the first charge storage among the plurality of charge storages.

Abstract: An endoscope using depth information and a method for detecting a polyp based on the endoscope using the depth information are provided. The endoscope using the depth information may generate an irradiated light signal including a visible light, obtain depth information based on the irradiated light signal and a reflected light signal obtained through the irradiated light signal being reflected off of an intestine wall, generate a depth image inside the intestine wall based on the depth information, and detect a polyp located on the intestine wall based on the depth image.

Abstract: A method and apparatus for processing a depth image that removes noise of a depth image may include a noise estimating unit to estimate noise of a depth image using an amplitude image, a super-pixel generating unit to generate a planar super-pixel based on depth information of the depth image and the noise estimated, and a noise removing unit to remove noise of the depth image using depth information of the depth image and depth information of the super-pixel.

Abstract: A depth noise filtering method and apparatus is provided. The depth noise filtering method may perform spatial filtering or temporal filtering according to depth information. In order to perform spatial filtering, the depth noise filtering method may determine a characteristic of a spatial filter based on depth information. Also, in order to perform temporal filtering, the depth noise filtering method may determine a number of reference frames based on depth information. The depth noise filtering method may adaptively remove depth noise according to depth information and thereby enhance a noise filtering performance.

Abstract: A method and apparatus for matching images are provided. The image matching method includes: obtaining a depth image and an intensity image of an object using a depth camera installed at a first position and a color image of the object using a color camera installed at a second position other than the first position; transforming the obtained depth image and intensity image into a depth image and an intensity image, respectively, that could be obtained if the object were photographed by a camera at the second position; and matching the transformed depth image and intensity image and the obtained color image. In this way, a depth image and intensity image obtained separately from a 2-dimensional (2D) color image can be accurately matched to the 2D color image, thereby allowing a reliable 3D image to be obtained.

Abstract: An integration time dynamic control apparatus and method for dynamically controlling an integration time of a depth camera based on a motion of a depth image, are provided to improve an accuracy of the depth image. The integration time dynamic control apparatus may measure a motion of a depth image acquired from the depth camera, may determine whether the measured motion is greater than or equal to a reference value set in advance, and may control the integration time of the depth camera based on a result of the determination, thereby improving the accuracy of the depth image.