Korea Advanced Institute of Science and Technology

Samsung Electronics Co., Ltd.

Junyong Noh

Bumki Kim

Kwanggyoon Seo

Seokpyo Hong

Kyungmin Cho

Jung-Hoon Han

Sangwoo Lee

Jungjin Lee

Haegwang Eom

Sungjin Kim

Junghoon Han

Yeonjin Lee

Minjung Choi

Sanghun Park

Sunjin Jung

Hanui Lee

Seokhwan Kim

Sung Yong Shin

Joodong Kim

Jaewon Seo

Jiwon Lee

Chaelin Kim

Jung Eun Yoo

Jaedong Kim

Gukho Kim

Julie Alfonsine E Lelong

Mohammad Reza Karimi Dastjerdi

Allen Kim

Daseong Han

Byungkuk Choi

Yeongho Seol

Jiyeon Kim

Junghwan Park

Hyeon-Woo Jang

Jaewoo Seo

Yunrae Cho

Seung Soo Kim

Byung Kuk Choi

Soojin Choi

Younghui Kim

Ha Young Chang

Dawon Lee

Hyunggoog Seo

Sihun Cha

Heonjun Lim

Kyehyun Kim

Amirsaman Ashtari

Roger Blanco I Ribera

J P Lewis

Ramakanth Kappaganthu

Sojung Lee

There is provided an apparatus for generating a 3D object texture map. The apparatus may comprise: a memory; and a processor, wherein the processor is configured to: generate a partial texture image by mapping object information in an input image into a texture space; obtain a sampling image by inputting the partial texture image to a sampler network trained according to a curriculum for selecting at least one of a training partial texture image, an aligned partial image in which the training partial texture image is aligned in the texture space, or an augmented partial image augmented from the aligned partial image; obtain a blending mask and a refined image by inputting the sampling image to a refiner network; and generate a 3D object texture map by blending the sampling image and the refined image based on the blending mask.

Apparatus and method for generating 3D object texture map, and recording medium storing instructions to perform method for generating 3D object texture map

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

Disclosed is an image processing method and apparatus. The image processing method includes extracting a content latent code and a style latent code for each of a plurality of input images, obtaining a content feature vector by calculating a weighted sum of content latent codes extracted from the input images based on a morphing control parameter, obtaining a style feature vector by calculating a weighted sum of style latent codes extracted from the input images based on the morphing control parameter, and generating a morphing image based on the content feature vector and the style feature vector.

Image processing method and apparatus

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

A method of training a deep neural network for generating a cinemagraph is disclosed. The method may include preparing a foreground layer input by using an input video, preparing a background layer input by using the input video, providing a foreground layer output and a background layer output from the DNN by inputting, to the DNN, the foreground layer input and the background layer input, providing an output video by synthesizing the foreground layer output with the background layer output, and updating intrinsic parameters of the DNN a plurality of times, based on the input video, the foreground layer input, the foreground layer output, the background layer output, and the output video.

Method of generating cinemagraph based on deep learning

A method of simulating a motion of an object controlling another object based on an example motion or a previously generated motion of the object is disclosed. The method includes refining a motion of a first object based on a motion of the first object predicted based on a motion specification, and on a trajectory of a second object controlled by the first object, and simulating the motion of the first object and the trajectory of the second object based on a vector for controlling joints of the first object that is generated based on the refined motion.

Method and apparatus for generating motion of object

A semiconductor device including a semiconductor substrate including a chip region and an edge region around the chip region; a lower dielectric layer and an upper dielectric layer on the semiconductor substrate; a redistribution chip pad that penetrates the upper dielectric layer on the chip region and is connected a chip pad; a process monitoring structure on the edge region; and dummy elements in the edge region and having an upper surface lower than an upper surface of the upper dielectric layer.

Semiconductor device

A motion processing method and apparatus are provided. The motion processing method includes obtaining a base-level motion by applying a linear Gaussian model to an input motion, obtaining a controllable motion displacement vector and a residual motion displacement vector by applying the linear Gaussian model to a displacement vector between the input motion and the base-level motion, and synthesizing an output motion based on the base-level motion and the controllable motion displacement vector.

Motion processing method and apparatus

Provided is a method of framing a three dimensional (3D) target object for generation of a virtual camera layout. The method may include analyzing a reference video image to extract a framing rule for at least one reference object in the reference video image, generating a framing rule for at least one 3D target object using the framing rule for the at least one reference object in the reference video image, and using the framing rule for the at least one 3D target object for generation of a virtual camera layout.

Method and apparatus for framing three dimensional target object for generation of virtual camera layout

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

A semiconductor chip includes a device layer on a substrate, the device layer including a plurality of semiconductor devices; a wiring structure and a lower inter-wiring dielectric layer each on the device layer, the lower inter-wiring dielectric layer surrounding the wiring structure and having a lower permittivity than silicon oxide; an upper inter-wiring dielectric layer arranged on the lower inter-wiring dielectric layer; an isolation recess arranged along an edge of the substrate, the isolation recess formed on side surfaces of the lower and upper inter-wiring dielectric layers and having a bottom surface at a level equal to or lower than that of a bottom surface of the lower inter-wiring dielectric layer; and a cover dielectric layer covering the side surfaces of the lower and upper inter-wiring dielectric layers and the bottom surface of the isolation recess.

Semiconductor chip including low-k dielectric layer

A semiconductor device includes a substrate including a first part and a second part, a memory cell disposed on the first part, an insulation layer disposed on the first part and the second part, the insulation layer covering the memory cell, a portion of the insulation layer on the second part including a stepped sidewall, and a first pattern group disposed on the second part and in the portion of the insulation layer and the substrate. A first sidewall of the semiconductor device corresponds to the stepped sidewall including an upper sidewall, a lower sidewall and a connecting surface connecting the upper sidewall to the lower sidewall. The lower sidewall disposed under the upper sidewall is closer to the substrate than the upper sidewall, and has surface roughness different from surface roughness of the upper sidewall.

Semiconductor devices including scribe lane and method of manufacturing the semiconductor devices

A character animation motion control method and device are disclosed. A character animation playing method, including extracting first actions based on a state of a character, extracting second actions based on the state, selecting an action included in the first actions and the second actions, and updating the state based on the action.

Method and device with character animation motion control

Growing community of inventors

Daejeon, South Korea

Junyong Noh