Samsung Electronics Co., Ltd.

Yonsei University

Technical University of Munich

Seoul National University

Nahyup Kang

Hyong Euk Lee

Hwiryong Jung

Jiyeon Kim

Donghoon Sagong

Inwoo Ha

Keechang Lee

Kyungboo Jung

Hyun Sung Chang

Wonhee Lee

Sunghoon Hong

Minjung Son

Jinwoo Kim

Young Hun Sung

Byung In Yoo

Byungin Yoo

Sangwon Lee

Chul Kyu Kang

Heesae Lee

Huijin Lee

Ji Yeon Kim

Kinam Kwon

Bohyung Han

Hyongeuk Lee

Yeonkyung Lee

Hyong-euk Lee

Jaeseok Choi

Seon Joo Kim

Mengyu Chu

Nils Thuerey

Junsang Yu

DongYoung Kim

Chu Woo Kang

Dong-Hwan Jang

A method with image processing includes: setting an offset window for an offset pattern of a kernel offset and an offset parameter for an application intensity of the kernel offset; determining an output kernel by applying the kernel offset to an input kernel based on the offset window and the offset parameter; and adjusting contrast of a degraded image using the output kernel.

Method and apparatus with contrast adjustment

A method and apparatus with image correction is provided. A processor-implemented method includes generating, using a neural network model provided an input image, an illumination map including illumination values dependent on respective color casts by one or more illuminants individually affecting each pixel of the input image, and generating a white-adjusted image by removing at least a portion of the color casts from the input image using the generated illumination map.

Method and apparatus with image correction

A three-dimensional (3D) rendering method includes extracting sample points from a 3D scene, acquiring rendering result information for the sample points by rendering the sample points, and generating a rendering result image corresponding to an entire rendering based on the rendering result information for the sample points and feature information of the 3D scene.

Three-dimensional (3D) rendering method and apparatus

An image restoration method includes determining an anchor image based on individual images of a burst image set, executing a feature extraction network based on the burst image set while using anchor information of the anchor image, and generating a restored image based on a feature map corresponding to an output of the feature extraction network.

Burst image-based image restoration method and apparatus

A modeling method searches for a sequence matched to a user input using a fluid animation graph generated based on similarities among frames included in sequences included in the fluid animation graph and models a movement corresponding to the user input based on a result of the searching. Provided also is a corresponding apparatus and a method for preprocessing for such modeling.

Modeling method and apparatus and apparatus using fluid animation graph

A processor-implemented method includes: estimating, from frame images of consecutive frames acquired from one or more sensors, short-term ego-motion information of the one or more sensors; estimating long-term ego-motion information of the one or more sensors from the frame images; determining attention information from the short-term ego-motion information and the long-term ego-motion information; and determining final long-term ego-motion information of a current frame, of the consecutive frames, based on the long-term ego-motion information and the attention information.

Method and apparatus with ego motion information estimation

A processor-implemented method of implementing an attention mechanism in a neural network includes obtaining key-value coupling data determined based on an operation between new key data determined using a first nonlinear transformation for key data of an attention layer, and value data of the attention layer corresponding to the key data; determining new query data by applying a second nonlinear transformation to query data corresponding to input data of the attention layer; and determining output data of the attention layer based on an operation between the new query data and the key-value coupling data.

Method and apparatus with key-value coupling

A method and apparatus for displaying a virtual route estimates a position of a vehicle based on sensing data received asynchronously from sensors, and outputs a three-dimensional (3D) virtual route generated by registering a driving environment model corresponding to a driving environment of the vehicle and the position of the vehicle in map information.

Method and apparatus for displaying virtual route

A vehicle localization method and a vehicle localization apparatus are disclosed. The vehicle localization method includes estimating an initial position of a vehicle based on data sensed by a position sensor, determining a driving lane of the vehicle based on a front-view image captured from the vehicle, correcting the initial position of the vehicle based on the driving lane, and determining a position of the vehicle in the driving lane based on geometry information of a lane boundary in the front-view image.

Vehicle localization method and apparatus

A localization method and apparatus are provided. The method comprises generating a synthetic image corresponding to a current time period based on a three-dimensional (3D) color map corresponding to an image captured at a time period prior to the current time period, and position information at the current time period time, and determining final position information at the current time period based on the synthetic image corresponding to the current time period and an image captured at the current time period.

Localization method and apparatus based on 3D color map

A processor-implemented learning method for an image segmentation includes training first duplicate layers, as duplications of trained first layers of a pre-trained model, so that a second feature extracted from a target image by the trained first duplicate layers is matched to a first feature extracted from a training image by the trained first layers; regularizing the trained first duplicate layers so that a similarity between the first feature and a third feature extracted from the training image by the regularized first duplicate layers meets a threshold; and training second duplicate layers, as duplications of trained second layers of the pre-trained model, to be configured to segment the target image based on the regularized first duplicate layers, the trained second layer being configured to segment the training image.

Method and apparatus with image segmentation

Modeling method and apparatus using fluid animation graph

A method of modeling an object includes defining a state transition probability and a state of each of a plurality of particles forming the object; changing a state of a particle defined to be in a first state among the plurality of particles to a second state; applying a movement model to a particle defined to be in the second state among the plurality of particles; and changing a state of the particle defined to be in the second state to the first state based on the state transition probability.

Method and apparatus for modeling object

A method and apparatus for identifying a driving lane extracts a road marking from an input image, generate a multi-virtual lane using the road marking and a segmentation image obtained by segmenting the input image into objects included in the input image based on a semantic unit, and identifies a driving lane of a vehicle based on a relative location of the driving lane in the multi-virtual lane.

Method and apparatus for identifying driving lane

Growing community of inventors

Seoul, South Korea

Nahyup Kang