Korea Advanced Institute of Science and Technology

Bumki Kim

Junyong Noh

Sangwoo Lee

Jungjin Lee

Hanui Lee

Jiwon Lee

Gukho Kim

Julie Alfonsine E Lelong

Mohammad Reza Karimi Dastjerdi

Allen Kim

Kwanggyoon Seo

Jaedong Kim

Younghui Kim

Hyunggoog Seo

Kyehyun Kim

An image processing device according to one embodiment estimates first optical flow information of a pixel unit on the basis of consecutive frames, and estimates a polynomial model corresponding to the optical flow information. The image processing device estimates second optical flow information of holes included in the frames on the basis of the polynomial model, and inpaints an input image on the basis of the first optical flow information and/or the second optical flow information.

Image processing method and device thereof

An image processing device according to one embodiment estimates optical flow information, pixel by pixel, on the basis of a reference image and input images of consecutive frames, and estimates a term corresponding to temporal consistency between the frames of the input images. The image processing device determines a mesh on the basis of the term corresponding to temporal consistency and the optical flow information, and transforms the reference image on the basis of the mesh. The image processing device preforms image blending on the basis of the input image, the transformed reference image, and mask data.

Image processing method and device therefor

A method of assisting object registration in a smart home system including a plurality of objects is disclosed. The disclosed method may include allowing a user to select an object from among a plurality of objects, capturing a plurality of pointing gestures by allowing the user to perform the plurality of pointing gestures at the selected object, configuring a pointing ray using each of the plurality of captured pointing gestures, estimating a position of a nearest point extending from the plurality of pointing rays, and registering the estimated position of the nearest point as a position of the selected object.

Method and apparatus for assisting object registration in a smart home system

The present disclosure relates to a method and a device for estimating suitability as a multi-screen projecting type theatre and the method for estimating the suitability as the multi-screen projecting type theatre includes: creating a plurality of image representation models (M) respectively corresponding to a plurality of candidate theatres; calculating a total image representation model ({circumflex over (M)}) corresponding to all of the plurality of candidate theatres; and calculating a deviation between the total image representation model ({circumflex over (M)}) and each of the plurality of image representation models (M) of the target theatre and estimating theatre suitability of the target theatre based on the deviation when one target theatre is selected among the plurality of candidate theatres.

Method for estimating suitability as multi-screen projecting type theatre system

The present disclosure relates to an image processing apparatus and method for transforming image data of a spherical coordinate system corresponding to image data of a planar coordinate system without transforming the image data of the planar coordinate system, and stitching the transformed image data of the spherical coordinate system to the image data of the planar coordinate system.

Image processing apparatus and method using video signal of planar coordinate system and spherical coordinate system

The present disclosure relates to an immersive display apparatus and method for creation of a peripheral view image corresponding to an input video, the method comprising a pre-processing step of obtaining scene-space information at a main-view video signal corresponding to a first area, a pre-warping step of performing first warping to at least one neighborhood frame corresponding to a target frame included in the pro-processed video signal and determining an outlier from the result of the first warping, a sampling step of sampling at least one neighborhood frame to be used for extrapolation from the result of the first warping, a warping step of performing second warping to the sampled frame except for the outlier to generate a peripheral view image signal corresponding to a second area around the first area, and a blending step of blending the peripheral view image signal to the main-view video signal.

Immersive display apparatus and method for creation of peripheral view corresponding to input video

The present invention includes a) creating geometry data of a theater screen, and mapping position information of seating on the geometry data to reconstruct a virtual theater structure, b) generating a grid mesh for each seat of the theater screen without changing edges of the theater screen, and c) generating a compensation map with minimized distortion of the grid mesh for each seat, and based on this, single-sampling compensating a pixel of an image to be displayed on the theater screen by the compensation map.

Growing community of inventors

Daejeon, South Korea

Bumki Kim