Samsung Electronics Co., Ltd.

Korea Advanced Institute of Science and Technology

Hitachi, Ltd.

Seungeon Kim

Jong Beom Ra

Kyoung-Yong Lee

Wonhee Lee

Toshihiro Rifu

Yongjin Chang

Seokhwan Jang

Duhgoon Lee

Iljun Ahn

Hyun Sung Chang

Minjung Son

Byung-sun Choi

JongHyon Yi

Youngwoo Park

Sangjun Park

Inwoo Ha

Kyungboo Jung

Jong-hyon Yi

Ji-young Choi

Kihong Son

Do Il Kim

Hyunsung Chang

Jong-Hyon Yi

A processor-implemented method with pose estimation includes: determining depth data by sensing a depth of a target scene comprising planes orthogonal to each other; determining normal vectors corresponding to depth points of the depth data; determining orientation data of a device by comparing the normal vectors to orientation candidates; and determining position data of the device based on distances from the device to the planes.

Method and apparatus with pose estimation

A display device may include: a display, a communication interface comprising circuitry configured to transmit and/or receive data to and from a plurality of electronic devices, a memory storing one or more instructions, and at least one processor configured to execute the one or more instructions to: split a screen of the display device into a plurality of regions and obtain pieces of display information respectively corresponding to the plurality of regions, control the communication interface to transmit first display information corresponding to a first region among the plurality of regions to a first electronic device corresponding to the first region among the plurality of electronic devices, receive, from the first electronic device, a first image obtained based on the first display information, and control the display to display the first image in the first region.

Display device and method for sharing screens of electronic devices

Provided is a method and apparatus for detecting a planar surface, the method including acquiring, based on a pixelwise disparity of an input image estimated in a first network, a pixelwise plane parameter of the input image, determining a pixelwise segment matching probability of the input image based on a second network trained to perform a segmentation of an image, acquiring a segment-wise plane parameter based on the pixelwise plane parameter and the pixelwise segment matching probability, and detecting a planar surface in the input image based on the segment-wise plane parameter.

Planar surface detection apparatus and method

A method and apparatus with depth map generation. The method may include generating points for a point cloud by unprojecting multi-view depth maps, of plural views, into a corresponding three-dimensional (3D) space using respective camera parameters corresponding to each view of the multi-view depth maps, extracting feature embedding vectors corresponding to the generated points, generating a two-dimensional (2D) feature map of a set view based on the extracted feature embedding vectors, generating a residual depth map using a refinement network with respect to the 2D feature map, generating a new depth map based on the residual depth map and an initial depth map, of the set view, among the multi-view depth maps.

Method and apparatus with depth map generation

Disclosed are an apparatus and method with video processing. A computing apparatus includes one or more processors and storage storing instructions configured to, when executed by the one or more processors, cause the one or more processors to: generate cluster maps using clusters generated by performing clustering, wherein the generating the cluster maps performed based on a reference frame of a video generated based on a previous point in time of the video, generate a predicted frame by performing motion compensation based on the cluster maps, and generate a decoded frame by performing decoding based on the current frame and the predicted frame.

Apparatus and method with video processing

A method and apparatus with image depth estimation are provided. The method includes obtaining a first statistical value associated with a depth for each of plural pixels included in an input image based on a first channel of output data obtained by applying the input image to a neural network, obtaining a second statistical value associated with a depth for each of the plural pixels in the input image based on a second channel of the output data, and estimating depth information of each of the plural pixels in the input image based on the first statistical value and the second statistical value. The neural network may be trained based on a probability distribution for a depth of each pixel in an image based on a first statistical value and a second statistical value that are obtained corresponding to an image with predetermined depth information in the training data.

Method and apparatus with image depth estimation

A method with algorithm updating includes: receiving a first input batch including one or more first images; generating a first output batch with respect to the first input batch using an algorithm configured to generate a disparity image, the first output batch including one or more first output images; receiving a second input batch corresponding to the first input batch, the second input batch including one or more second images having viewpoints that are different from viewpoints of the one or more first images; generating a test batch based on the first output batch and the second input batch, the test batch including one or more test images; and updating the algorithm based on a difference between the first input batch and the test batch.

Method and apparatus with updating of algorithm for generating disparity image

A medical imaging apparatus includes an X-ray source configured to irradiate X-rays to an object; an X-ray detector configured to detect the X-rays radiated from the X-ray source to obtain projection data; and an image processor configured to reconstruct the projection data based on a motion parameter representing movement of at least one of the object, the X-ray source, and the X-ray detector, and to generate a medical image by applying a weighting process to the reconstructed projection data.

Workstation, medical imaging device including same, and control method therefor

Provided are a tomography imaging apparatus and a method of reconstructing a tomography image which may more accurately measure a motion of an object to be tomography-imaged. In detail, the tomography imaging apparatus and the method of reconstructing a tomography image may obtain information indicating a motion of a moving object according to a time, may perform motion correction based on the obtained motion information, and may reconstruct a target image with reduced motion artifacts.

Tomography imaging apparatus and method of reconstructing tomography image

A tomography apparatus includes a data acquirer configured to acquire partial images of an object including a first image and a second image having imaged a surface of a portion of the object corresponding to a first time and a second time, respectively, by performing a tomography scan on the object that is moving, and acquire first information indicating motion of the object by using the first image and the second image; and an image reconstructor configured to reconstruct a target image by using the first information.

Tomography apparatus and method for reconstructing tomography image thereof

Provided is a medical image processing apparatus including a processor. The processor obtains raw data in a first phase section and generates first motion information by using at least one partial angle reconstruction (PAR) image pair including two PAR images respectively obtained in two phase sections in the first phase section that face each other. The processor also generates a summed image by summing a plurality of PAR images obtained at different phases within the first phase section by using the first motion information Second motion information is generated by updating the first motion information such that an image metric representing motion artifacts is minimized when being calculated from the summed image and a reconstructed image is generated by applying the second motion information to the raw data.

Method and apparatus for processing a medical image to reduce motion artifacts

A tomography apparatus includes a data acquirer acquiring a first image and a second image that are partial images, by using data acquired in a first angular section corresponding to a first time point and a second angular section corresponding to a second time and facing the first angular section, by performing a tomography scan on an object that is moving, and acquiring first information indicating a motion amount of the object by using the first image and the second image, and an image reconstructor reconstructing a target image indicating the object at a target time, based on the first information.

A tomography apparatus includes a data acquirer which acquires a first image which corresponds to a first time point and a second image which corresponds to a second time point by performing a tomography scan on an object; an image reconstructor which acquires first information which relates to a relationship between a motion amount of the object and the time based on a motion amount between the first image and the second image, predicts a third image which corresponds to a third time point between the first and second time points based on the first information, corrects the first information by using the predicted third image and measured data which corresponds to the third time point, and reconstructs the third image by using the corrected first information; and a display which displays the reconstructed third image.

Growing community of inventors

Bucheon-si, South Korea

Seungeon Kim