Lg Electronics Inc.

Samsung Electronics Co., Ltd.

Intel Corporation

Universitéde Montreal

University of Montreal

Taesup Kim

Sehoon Yea

Jin Seong Heo

Jiwook Jung

Moonmo Koo

Jaewon Sung

Eunyong Son

Junghak Nam

Sunmi Yoo Yoo

Jungdong Seo

Hongmo Je

Tae-Hoon Kim

Hyungsoo Lee

Minje Park

Sanghyun Yoo

Inchul Song

Yeongjae Cheon

Dmytro Rusanovskyy

Junyoung Chung

Sehoon Yae

A speech recognition method includes obtaining an acoustic sequence divided into a plurality of frames, and determining pronunciations in the acoustic sequence by predicting a duration of a same pronunciation in the acoustic sequence and skipping a pronunciation prediction for a frame corresponding to the duration.

Speech recognition method and apparatus

A method for processing video signals by a decoding apparatus includes determining whether the temporal neighboring block of a current texture block is coded using inter-view prediction; and determining whether the spatial neighboring block of the current texture block is coded using inter-view prediction. When the temporal neighboring block and the spatial neighboring block are not coded using the inter-view prediction, deriving an inter-view motion vector of the current texture block as a disparity vector, and performing inter-view prediction for the current texture block using the derived inter-view motion vector of the current texture block. The disparity vector is obtained using a depth value according the current texture block.

Method and apparatus for processing video signals using inter-view inter-prediction

According to the present invention, an inter-view motion vector of a current coding unit is acquired using parallel processing information, and a motion vector of a current prediction unit in the current coding unit is acquired in parallel using the inter-view motion vector of the current coding unit. The present invention relates to a method and device for processing a video signal, wherein a motion vector prediction value of the current prediction unit is acquired by comparing output order information of a reference picture corresponding to the current prediction unit and output order information of a reference picture corresponding to a corresponding block. According to the present invention, through a parallel processing step, a multi-view point video image can be quickly restored, and the accuracy of the motion vector prediction value can be increased using motion information corresponding to the reference picture of the corresponding block of a different view point from the current prediction unit.

Method and device for processing video signal

The present invention relates to a method and an apparatus for processing a video signal. The present invention can acquire an inter-view motion vector of a current block, acquire a first corresponding block by using the inter-view motion vector, identify a prediction method of the first corresponding block, acquire a second corresponding block when the first corresponding block is not coded by a time inter prediction, acquire a time motion vector of the second corresponding block, acquire a time motion vector of the current block by using the time motion vector of the second corresponding block, and decode the current block by using the time motion vector of the current block.

Method and apparatus for processing video signal

The present invention relates to a method and an apparatus for coding a video signal, and more specifically, a motion vector between viewpoints is obtained by using a depth value of a depth block, which corresponds to a current texture block, and an illumination difference is compensated. By obtaining the motion vector between the viewpoints by using the depth value of the depth block, which corresponds to the current texture block, and compensating the illumination difference, the present invention can obtain an accurate prediction value of the current texture block and thus increase accuracy in inter-prediction between the viewpoints.

The present invention relates to a video signal processing method and device capable of: obtaining a reference view block by using a predetermined motion vector; obtaining the depth value of a reference block which corresponds to the reference view block; obtaining an inter-view motion vector for a current block by using at least one depth value of the reference depth block; and decoding the current block by using the inter-view motion vector.

Video signal processing method and device

The present invention relates to a method for constituting a merge candidate list by using a view synthesis prediction (VSP) and the like in multi-view video coding. The method for constituting the merge candidate list according to the present invention comprises the steps of: determining a prediction mode for a current block; inducing, as a merge candidate, motion information from neighboring blocks of the current block when the prediction mode for the current block is a merge mode or a skip mode; and constituting the merge candidate list by using the motion information of the neighboring blocks and the deep parity information induced from the neighboring blocks of the current block.

Method predicting view synthesis in multi-view video coding and method for constituting merge candidate list by using same

A method inducing video information required for decoding a current block by entropy-decoding a bitstream; inducing a first disparity vector based on a neighboring block of the current block in the same view by using the video information, inducing a second disparity vector by using the first disparity vector and a reference view depth, and inducing a third disparity vector using the difference between the first disparity vector and the second disparity vector; inducing a prediction sample of the current block by using one of the first disparity vector, the second disparity vector, or the third disparity vector; and applying filtering to a current picture which has been restored using the prediction sample.

Video decoding apparatus and method for decoding multi-view video

The present invention relates to a video decoding apparatus and a method for decoding a multi-view video, and the video decoding apparatus according to the present invention comprises: an entropy-decoding unit for entropy-decoding a bitstream and outputting video information required for decoding a current block in a depth picture; a memory for saving pictures referenced when decoding the current block; and a prediction unit for inducing a prediction sample of the current block, by using motion information of a texture picture within the same view as motion information of the current block.

Method and apparatus for decoding multi-view video

The present invention relates to inter-view residual prediction and is characterized by obtaining residual data of a first reference block by using a motion vector of a neighboring block, obtaining residual data of a second reference block by using a reference view motion vector or a disparity vector, obtaining a residual data prediction value by using the residual data of the first reference block and the residual data of the second reference block, and coding a current texture block by using the residual data prediction value. The present invention can perform inter-view residual prediction by using a prediction value obtained using coded data of another view point belonging to the same time band to increase the accuracy of video data prediction by using a correlation between view points and reduce the amount of residual data to be transmitted, thereby improving the coding efficiency. In addition, the complexity in coding process may be reduced by adding a condition for applying the inter-view residual prediction.

The present invention relates to a method and an apparatus for processing video signals, and more specifically, to a method and an apparatus for processing video signals which applies deformation compensation to decode a current texture block. The present invention can increase the accuracy of an inter-prediction by obtaining the position of a block within a reference picture referenced by the current texture block, by means of using deformation compensation parameter information, and obtaining a pixel value of the block within the reference picture that is obtained from a prediction value of the current texture block.

Method and apparatus for processing video signals

The present invention relates to a method and an apparatus for processing a video signal, the method comprising: receiving a multiview video signal; identifying whether a current picture including a first layer and a second layer is decoded by using alpha data within the multiview video signal; obtaining the alpha data corresponding to the first layer and the second layer when the current picture is identified to be decoded by using the alpha data; and decoding a current block included in the current picture by using the alpha data, wherein the alpha data may include information concerning transparency information of the current picture.

The present invention variably adjusts the maximum splitting information of a conversion unit according to the type of prediction unit and the splitting information on a coding unit and selects the optimal splitting information on the conversion unit. The present invention determines the maximum splitting information on the conversion unit of a depth block by using the maximum splitting information on the conversion unit for texture data. The present invention may lower complexity without a loss in efficiency by variably adjusting the maximum splitting information on the conversion unit in consideration of the characteristics of the depth data. The present invention may lower complexity by determining the maximum splitting information on the conversion unit of the depth data by using similar characteristics between the texture data and the depth data.

Method and device for determining a unit of a transform unit used in video signal processing

The present invention relates to a method for processing a video signal and a video decoder, wherein an offset parameter of a reference block is acquired, an offset parameter of a current block is acquired by using the offset parameter of the reference block, an adaptive parameter is applied to the current block by using the offset parameter of the current block, and the reference block is a block in a different view point from the current block. According to the present invention, an accurate adaptive parameter can be applied to the current block by using an offset parameter of a reference view point in consideration of a difference between view points when obtaining the offset parameter of the current block.

According to the present invention, a method for processing video signals can determine an interview motion vector of a current block using an interview motion vector of a temporal neighboring block in consideration of a global motion vector. The present invention can obtain an accurate interview motion vector according to obtaining the temporal neighboring block of the current block in consideration of a motion change according to output sequence information and accordingly, can increase the accuracy of inter-prediction.

Growing community of inventors

Seoul, South Korea

Taesup Kim