Samsung Electronics Co., Ltd.

Weiming Li

Haitao Wang

Tao Hong

Mingcai Zhou

Qiang Wang

Yang Liu

Hao Wang

Sunghoon Hong

Yueying Kao

Zhihua Liu

Xiying Wang

Zairan Wang

Lin Ma

Chao Zhang

Jiyeon Kim

Hyun Sung Chang

Gengyu Ma

Shaohui Jiao

Kang Xue

Dong Kyung Nam

Dongkyung Nam

Jinho Lee

Hyong Euk Lee

Minsu Ahn

Wooshik Kim

Seungin Park

Ji Yeun Kim

Dongdong Yu

Chun Long Wang

Jingu Heo

Shandong Wang

Yang Ho Cho

Wenbo Zhang

Jie Dong

Myungjae Jeon

Dongwoo Kang

Hyoseok Hwang

Deheng Qian

Guangwei Wang

YangHo Cho

Ya Lu

Mingcai Zho

Bao He

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 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

A method with image processing includes: determining a feature map of an image; determining a spatial position weight of pixel points of the feature map; determining a corrected feature map by correcting the feature map based on the spatial position weight of the pixel points; and determining a key point based on the corrected feature map.

Method and apparatus with image processing

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

An electronic device for estimating object information and generating a virtual object and a method of operating the electronic device are disclosed. The method includes obtaining an image, obtaining a class feature, a pose feature, and a relationship feature of an object included in the image, correcting each of the class feature, the pose feature, and the relationship feature using any combination of any two or more of the class feature, the pose feature, and the relationship feature of the object, and obtaining class information, pose information, and relationship information of the object based on the corrected class feature, the corrected pose feature, and the corrected relationship feature, respectively.

Method and apparatus with object information estimation and virtual object generation

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

An image processing apparatus and method are provided. The image processing apparatus acquires a target image including a depth image of a scene, determines three-dimensional (3D) point cloud data corresponding to the depth image based on the depth image, and extracts an object included in the scene to acquire an object extraction result based on the 3D point cloud data.

Image processing apparatus and method

Embodiments of the present invention provide an Augmented Reality (AR) method and apparatus for driving assistance, which are applied in the technical field of AR. The method comprises the steps of: determining, based on information acquired during the driving process, driving assistance information, and displaying virtual three dimensional (3D) display information corresponding to the driving assistance information. In the present invention, the AR technology can be applied in the vehicle travelling process to assist a driver in better mastering driving information in the vehicle travelling process, and the user experience can be improved.

Augmented reality method and apparatus for driving assistance

The present invention provides a method and device for adjusting resolution of a Head-Mounted Display (HMD) apparatus. Wherein, the method comprises the steps of: determining saliency information of display contents in multimedia information; adjusting, according to the saliency information, resolution corresponding to each display content in the multimedia information; and, displaying the resolution-adjusted multimedia information. In the present invention, by determining saliency information of display contents in multimedia information, the resolution corresponding to the display contents is adjusted, which enable the resolution of the display contents to be matched with the saliency of the display contents, and accordingly, the resolution-adjusted multimedia information is displayed without the need of displaying the complete multimedia information in a higher resolution and a higher frame rate. In this way, computation amount for a device is greatly reduced, so that requirement for device hardware is reduced and device cost is reduced, and displaying efficiency is improved whilst at the same time ensuring good displaying effect.

Method and device for adjusting resolution of HMD apparatus

An object detection method includes setting a first window region and a second window region larger than the first window region that correspond to partial regions of different sizes in an input image, downsampling the second window region to generate a resized second window region, detecting a first object candidate from the first window region and a second object candidate from the resized second window region, and detecting an object included in the input image based on one or both of the first object candidate and the second object candidate.

Method and apparatus for detecting object

A method and apparatus for controlling an augmented reality (AR) apparatus are provided. The method includes acquiring a video, detecting a human body from the acquired video, performing an action prediction with regard to the detected human body, and controlling the AR apparatus based on a result of the action prediction and a mapping relationship between human body actions and AR functions.

Method and apparatus that controls augmented reality (AR) apparatus based on action prediction

Provided is a method and apparatus for aligning a three-dimensional (3D) model. The 3D model alignment method includes acquiring, by a processor, at least one two-dimensional (2D) image including an object, detecting, by the processor, a feature point of the object in the at least one 2D input image using a neural network, estimating, by the processor, a 3D pose of the object in the at least one 2D input image using the neural network, retrieving, by the processor, a target 3D model based on the estimated 3D pose, and aligning, by the processor, the target 3D model and the object based on the feature point.

Method and apparatus for aligning 3D model

The method of the present invention for processing a video comprises: acquiring a first and a second omnidirectional videos having a stereoscopic parallax in a first direction which is a corresponding column direction when the first and the second omnidirectional videos are unfolded by longitude and latitude; and, determining one or two third omnidirectional videos according to the first and the second omnidirectional videos, the second and the third omnidirectional videos having a stereoscopic parallax in a second direction, wherein, if one third omnidirectional video is determined, the second and the third omnidirectional videos have a stereoscopic parallax in the second direction; if two third omnidirectional videos are determined, the two third omnidirectional videos have a stereoscopic parallax in the second direction; and, the second direction is a corresponding row direction when the first and the second omnidirectional videos are unfolded by longitude and latitude.

Method and device for processing video

Growing community of inventors

Beijing, China

Weiming Li