Electronics and Telecommunications Research Institute

The Industry & Academic Cooperation in Chungnam National University (iac)

Gi-Mun Um

Gun Bang

Nam Ho Hur

Soo In Lee

Eun Young Chang

Tae One Kim

Soo-In Lee

Jin-Woong Kim

Hee-Kyung Lee

Hong-Chang Shin

Taeone Kim

Eun-Young Chang

Nam-Ho Hur

Won-Sik Cheong

Namho Hur

Hong Chang Shin

Sang-Woon Kwak

Joung-Il Yun

Dae-Young Song

Dong-Hyeon Cho

Seong-Yong Lim

Disclosed herein are a method and apparatus for generating a panoramic image. The method includes configuring a data set for training a deep learning network based on K images, extracting an encoding feature map, a skip connection feature map, and a decoding feature map based on K/2 images, among the images, estimating multiple homographies based on the encoding feature map, estimating a flow adjustment map, a preprocessing blending map, a weight map, and a post-processing blending map based on the decoding feature map, deriving a flow map based on the multiple homographies and the flow adjustment map, generating a preprocessed image based on the preprocessing blending map, generating multiple warped images based on the preprocessed image and the flow map, generating a matching image based on the warped images and the weight map, and correcting the matching image based on the matching image and the post-processing blending map.

Method and apparatus for generating panoramic image based on deep learning network

Disclosed herein are an apparatus and method for 360-degree video stitching. The apparatus for 360-degree video stitching includes memory for storing at least one program, and a processor for executing the program, wherein the program is configured to stitch features of multiple input images based on at least one parameter included in a 360-degree stitching function description template, and then creating a single 360-degree video, the 360-degree stitching function description template includes a configuration parameter that is an array of function parameters, the configuration parameter includes a stitching parameter, a camera parameter, a feature parameter, and a projection parameter, the feature parameter includes a method for extracting respective features from multiple input images, and the projection parameter includes a projection type that is a kind of a projection plane onto which the multiple input images are projected.

Apparatus and method for 360-degree video stitching

Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.

Apparatus and method for synthesizing virtual viewpoint images

Provided is a multi-view video coding/decoding method and apparatus which uses coded and decoded multi-view videos to code and decode depth information videos corresponding to the multi-view videos. The multi-view video coding method includes: controlling the scales of first and second depth information videos corresponding to a multi-view video such that the scales are equalized; and coding the second depth information video, of which the scale is controlled, by referring to the first depth information video of which the scale is controlled.

Multi-view video coding/decoding method and apparatus

A device for creating multi-view video contents includes a virtual view position and distribution unit that calculates a plurality of virtual views corresponding to the number of predetermined virtual views based on input information and distributes the calculated positions of the plurality of virtual views to a plurality of view synthesis processing units; a view synthesis processor that operates the plurality of view synthesis processing units in parallel, allows each of the view synthesis processing units to create at least one virtual view video corresponding to a position of at least one virtual view distributed from the virtual view position calculation and distribution unit, and performs partial multiplexing based on at least one created virtual view video; and a video integration unit that integrates a plurality of partially multiplexed videos output from the plurality of view synthesis processing units.

Device and method for creating multi-view video contents using parallel processing

Method and device for generating a multi-viewpoint image are provided. The method of generating a multi-viewpoint image includes the steps of: acquiring at least one reference-viewpoint image; generating unit image information of a virtual-viewpoint image on the basis of unit image information of the reference-viewpoint image; multiplexing the unit image information of the reference-viewpoint image and the unit image information of the virtual-viewpoint image; and generating a multi-viewpoint image by performing an interpolation process on occluded areas between the multiplexed unit image information using the multiplexed unit image information. As a result, it is possible to avoid unnecessary processes of completing and rearranging individual viewpoint images in the course of generating a multi-viewpoint image.

Method and device for generating multi-viewpoint image

A method and a device for adjusting depth perception, a terminal including a function for adjusting depth perception and a method for operating the terminal are provided. The method for adjusting depth perception includes: obtaining color and depth videos of a user; detecting a user's position based on the obtained depth video of the user; calculating a range of maximum and minimum depths in a 3-dimensional (3D) video according to the detected user's position; and adjusting a left and right stereo video generating interval of the 3D video to be rendered so as to satisfy the calculated range of the maximum and minimum depths. Therefore, during a 3D or multi-view video call, the 3D video having a three-dimensional effect optimized according to the user's position may be provided.

Method and device for adjusting depth perception, terminal including function for adjusting depth perception and method for operating the terminal

A method and apparatus for enhancing quality of a depth image are provided. A method for enhancing quality of a depth image includes: receiving a multi-view image including a left image, a right image, and a center image; receiving a current depth image frame and a previous depth image frame of the current depth image frame; setting an intensity difference value corresponding to a specific disparity value of the current depth image frame by using the current depth image frame and the previous depth image frame; setting a disparity value range including the specific disparity value; and setting an intensity difference value corresponding to the disparity value range of the current depth image frame by using the multi-viewpoint image.

Growing community of inventors

Daejeon-si, South Korea

Gi-Mun Um