Samsung Electronics Co., Ltd.

Samsung Display Co., Ltd.

Korea Advanced Institute of Science and Technology

Jiyeon Kim

Jaehan Lee

Saebyuk Sheen

Nari Choi

Hyong Euk Lee

Junho Choi

Nahyup Kang

Hyungmin Kim

Hoik Hwang

Hwiryong Jung

Minsu Ahn

Saebyuk Shin

Hyun Sung Chang

Qiang Wang

Sunghoon Hong

Jaemyoung Lee

Weiming Li

Woojin Jung

Donghoon Sagong

Yang Liu

Hao Wang

Jin Hwan Choi

Dongwon Choi

Minjung Son

Seungin Park

Yueying Kao

Hwajun Lee

Young Hun Sung

Chao Zhang

Hyun Joo Lee

Hyun Gu Kim

Beomjin Kim

Jonghwa Lee

Minhee Kang

Jiyoun Kim

Kwansuk Yoo

Sungsu Park

Tae-ho Kim

Sunyoung Lee

Sang-Il Park

Lin Ma

Taewoong Kim

Younghak Oh

Jungwoo Choi

Tae Woong Kim

Kyungmin Lee

Youngseong Kim

Hyosang Bang

Inwoo Ha

Seungyong Lee

Heekyung Jeon

Wooshik Kim

Hankyung Jeon

Junyong Noh

Seockhyun Yu

Nari Kim

Kwanghyun Jang

Hwayong Kang

Hyunyeul Lee

Yongkoo Lee

Sanghyuk Koh

Chanwoo Kim

Youngmi Kim

Changwoo Han

Jiwon Jeon

Soeyoun Yim

Sangsu Lee

Jinhoon Cho

Jaegi Han

Seokpyo Hong

Sangjun Lee

Youngjay Lee

Kyungyul Seo

Jaeho Ahn

Jaehoon Jeong

Kyungmin Cho

Seungwook Nam

Myung-hwan Kim

Martin Jung

Hyewon Moon

Jihyun Um

KwangHyun Jang

Hyong-euk Lee

Chaelin Kim

Ikhyung Park

Soojin Choi

An electronic device and method with gaze estimating are disclosed. The method includes obtaining target information of an image, the image including an eye, obtaining a target feature map representing information on the eye in the image based on the target information, and estimating a gaze for the eye in the image based on the target feature map. The target information includes either attention information on the image, or a distance between pixels in the image, or both.

Device and method with gaze estimating

A display device includes a display module, a support layer disposed below the display module, a support layer disposed below the display module, and including a rolling portion wound and unwound in a first direction, where the rolling portion includes a central portion, a first region between a first edge of the rolling portion and the central portion, and a second region between a second edge of the rolling portion and the central portion, a first support bar disposed in the central portion, second support bars disposed in the first region, and third support bars disposed in the second region. A width of each of the second support bars in the first direction is greater than a width of the first support bar, and widths of the second support bars in the first direction gradually increase as being closer to the first edge.

Display device

A display device includes a display module rollable in a rolling direction, and a support member facing the display module and rollable together with the display module. The support member includes a plurality of support bars arranged along the rolling direction, and a support layer which is between the display module and the plurality of support bars. Each of the plurality of support bars includes first and second portions at opposing ends of the support bar, along a direction crossing the rolling direction, and a third support portion between the first and second support portions, connecting the first support portion to the second support portion, and corresponding to the display module, where a thickness of each of the first support portion and the second support portion is greater than a thickness of the third support portion.

Support structure and display device having the same

A method with object pose estimation includes: obtaining an instance segmentation image and a normalized object coordinate space (NOCS) map by processing an input single-frame image using a deep neural network (DNN); obtaining a two-dimensional and three-dimensional (2D-3D) mapping relationship based on the instance segmentation image and the NOCS map; and determining a pose of an object instance in the input single-frame image based on the 2D-3D mapping relationship.

Method and apparatus with object pose estimation

An apparatus transfers object motion in a source space to a target space. The apparatus defines a mapping function from the source space to the target space based on feature points of the object-positioned source space, and feature points of the object-represented target space; determines a target root position corresponding to a root position of the object based on the mapping function; determines a target direction corresponding to a direction of the object, based on the mapping function; determines a target main joint corresponding to a main joint of the object based on the mapping function; determines a target sub-joint excluding the target main joint in the target space based on unique joint information of the object; and generates data representing the object motion in the target space by modifying a pose of the object in the target space to match the target main joint.

Method and apparatus with object motion transfer

Remote controller

A display module including a display unit and a support member disposed below the display unit and including first areas and second areas. The support member includes a matrix, a first supporter disposed in the matrix and including first extension parts, each extending in a first direction and spaced apart from each other in a second direction crossing the first direction, and a second supporter disposed in the matrix and including second extension parts, each extending in the first direction and spaced apart from each other in the second direction, and connection parts disposed between the second extension parts, where the second extension parts and the connection parts define openings in the second supporter.

Rollable display device

A method with object detection includes obtaining a first point cloud feature based on point cloud data of an image and determining at least one object in the image based on the first point cloud feature.

Method and apparatus with object detection

A method with global localization includes: extracting a feature by applying an input image to a first network; estimating a coordinate map corresponding to the input image by applying the extracted feature to a second network; and estimating a pose corresponding to the input image based on the estimated coordinate map, wherein either one or both of the first network and the second network is trained based on either one or both of: a first generative adversarial network (GAN) loss determined based on a first feature extracted by the first network based on a synthetic image determined by three-dimensional (3D) map data and a second feature extracted by the first network based on a real image; and a second GAN loss determined based on a first coordinate map estimated by the second network based on the first feature and a second coordinate map estimated by the second network based on the second feature.

Method and apparatus with global localization

A processor-implemented method with object pose estimation includes: determining an image feature corresponding to a point cloud of an input image; determining semantic segmentation information, instance mask information, and keypoint information of an object, based on the image feature; and estimating a pose of the object based on the semantic segmentation information, the instance mask information, and the keypoint information.

A method, an apparatus, an electronic device for estimating a pose of an object include determining a confidence of a depth image of an object based on a color image and the depth image of the object, estimating a pose of the object based on a three-dimensional (3D) keypoint in response to the depth image being reliable, and estimating the pose of the object based on a two-dimensional (2D) keypoint in response to the depth image being unreliable.

Method, apparatus, electronic device and storage medium for estimating object pose

Electronic games console

Display screen or portion thereof with transitional graphical user interface

A processor-implemented method with three-dimensional (3D) modeling includes: determining a type of movement of an object detected in an image received from a sensor, based on a variability of a position of the object and a variability of a shape of the object; segmenting the object into one or more chunks each corresponding to a unit of movement, based on the determined type of movement; correcting the determined type of movement based on a change in position of one or more feature points of the one or more chunks of the object in the image; determining a state of the movement of the object based on the corrected type of the movement of the object; correcting a pose of the sensor based on a state of the object; and updating a pose for each of the one or more chunks of the object based on the determined state of the object and the corrected pose of the sensor.

Apparatus and method with 3D modeling

Growing community of inventors

Hwaseong-si, South Korea

Jiyeon Kim