Electronics and Telecommunications Research Institute

Information Technology University (itu)

Etri

Seoul National University

Jeong Il Seo

Kyeong Ok Kang

Seung Kwon Beack

Jin Woong Kim

Dae Young Jang

Tae Jin Lee

Yong Ju Lee

Jong Mo Sung

Jae Hyoun Yoo

Tae Jin Park

Keun Woo Choi

Yong Ju Cho

Jin Soo Choi

Soon Heung Jung

Seong Yong Lim

In Seon Jang

Seung Chul Ham

Hui Yong Kim

Min Soo Kim

Jin Woo Hong

Hyun Cheol Kim

Won Sik Cheong

Jae-hyoun Yoo

Gi Mun Um

Philip Arthur Nelson

Joo Myoung Seok

Min Cheol Shin

Filippo Fazi

Sang Woo Ahn

Joung Il Yun

Jung Woo Choi

Hee Kyung Lee

Min Soo Hahn

Rehan Hafiz

Seung Jun Yang

Hyun Joo Chung

Sang Bae Chon

Koeng Mo Sung

Muhammad Faisal

Mohsen Ali

Hyuk Min Kwon

Aman Irshad

Keunwoo Choi

Koang Mo Sung

Seung Kwon Dormitory Of Info & Com Uni Beack

Kwang Ki Kim

Han Gil Moon

Seung Kwon Information And Communication Beack

Disclosed is an apparatus and method for processing a multichannel audio signal. A multichannel audio signal processing method may include: generating an N-channel audio signal of N channels by down-mixing an M-channel audio signal of M channels; and generating a stereo audio signal by performing binaural rendering of the N-channel audio signal.

Apparatus and method for processing multi-channel audio signal

An encoding/decoding apparatus and method for controlling a channel signal is disclosed, wherein the encoding apparatus may include an encoder to encode an object signal, a channel signal, and rendering information for the channel signal, and a bit stream generator to generate, as a bit stream, the encoded object signal, the encoded channel signal, and the encoded rendering information for the channel signal.

Encoding/decoding apparatus for processing channel signal and method

Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.

Method of training image deep learning model and device thereof

Disclosed herein is a method of creating an image stitching workflow including acquiring 360-degree virtual reality (VR) image parameters necessary to makes a request for image stitching and create the image stitching workflow, acquiring a list of functions applicable to the image stitching workflow, creating the image stitching workflow based on functions selected from the list of functions, determining the number of media processing entities necessary to perform tasks configuring the image stitching workflow and generating a plurality of media processing entities according to the determined number of media processing entities, and allocating the tasks configuring the image stitching workflow to the plurality of media processing entities.

Method and apparatus for providing 360 stitching workflow and parameter

Disclosed is a binaural rendering method and apparatus for decoding a multichannel audio signal. The binaural rendering method may include: extracting an early reflection component and a late reverberation component from a binaural filter; generating a stereo audio signal by performing binaural rendering of a multichannel audio signal base on the early reflection component; and applying the late reverberation component to the generated stereo audio signal.

Binaural rendering method and apparatus for decoding multi channel audio

Disclosed herein a method of removing a point cloud outlier and an apparatus implementing the method. The method includes: arranging a point cloud obtained from a laser scanner along at least a first direction; selecting, neighboring first-axis points, between which a separation degree satisfies an inspection start threshold condition, as a first leading-side representative point and a first trailing-side representative point; selecting a first leading-side outlier candidate and a first trailing-side outlier candidate based on a first leading-side separation degree and a first trailing-side separation degree; and determining the first leading-side outlier candidate and the first trailing-side outlier candidate as a first outlier point, when the number of the outlier candidates satisfies an allowable threshold condition.

Method of removing outlier of point cloud and apparatus implementing the same

An encoding method for a multi-channel audio signal, an encoding apparatus for performing the encoding method, and a decoding method for a multi-channel audio signal and a decoding apparatus for performing the decoding method are disclosed. A method and apparatus of bypassing an MPEG Surround (MPS) standard operation and using an arbitrary tree when a number of audio signals of N channels exceeds a channel number defined in an MPS standard, is disclosed.

Encoding method and encoder for multi-channel audio signal, and decoding method and decoder for multi-channel audio signal

An audio encoding apparatus and method that encodes hybrid contents including an object sound, a background sound, and metadata, and an audio decoding apparatus and method that decodes the encoded hybrid contents are provided. The audio encoding apparatus may include a mixing unit to generate an intermediate channel signal by mixing a background sound and an object sound, a matrix information encoding unit to encode matrix information used for the mixing, an audio encoding unit to encode the intermediate channel signal, and a metadata encoding unit to encode metadata including control information of the object sound.

Audio encoding apparatus and method, audio decoding apparatus and method, and audio reproducing apparatus

Encoding/decoding apparatus for processing channel signal and method therefor

The present invention provides a method for image preprocessing, the method including: identifying a plurality of input images to process image registration; selecting at least one transformation method among histogram equalization and gamma transformation in consideration of hue and brightness values of the plurality of input images; processing the histogram equalization on the plurality of input images in response to the histogram equalization method being selected; and processing the gamma transformation on the plurality of input images, in response to the gamma transformation method being selected.

Method and apparatus for image preprocessing

An encoder and an encoding method for a multi-channel signal, and a decoder and a decoding method for a multi-channel signal are disclosed. A multi-channel signal may be efficiently processed by consecutive downmixing or upmixing.

Encoder and encoding method for multi-channel signal, and decoder and decoding method for multi-channel signal

The present invention relates to an apparatus and a method of stitching a real-time image. More specifically, stitching-related information is generated, a parallax occurrence region in an overlap region is tracked, and correction for reducing parallax occurring in the parallax occurrence region and correction of an image distortion occurring in a non-overlap region are performed for output.

Apparatus and method of parallax-minimized stitching by using HLBP descriptor information

Growing community of inventors

Daejeon, South Korea

Jeong Il Seo