Sharp Kabushiki Kaisha Corporation

Keiichiro Takada

Tomohiro Ikai

Tomoko Aono

Takeshi Chujoh

Yukinobu Yasugi

Yasuaki Tokumo

Tomonori Hashimoto

Sachin G Deshpande

In a case that all network parameters are adaptively switched, it is difficult to switch the parameters for each small block, such as a CTU. There is a problem in that, in a case that ALF class classification and filtering are successively performed in ALF parallel after application of an NN filter, processing requires time. By selecting an NN model in a slice header and selecting a network layer finetuned in a CTU, the NN model can be adaptively selected even for each small block. By performing ALF class classification in an image before being subjected to an NN filter and performing ALF processing using an image subjected to NN filtering processing and ALF class information, the NN filtering processing and the ALF class classification can be performed in parallel.

Video coding apparatus and video decoding apparatus

A device may comprise one or more processors configured to: derive variables BitDepthY and BitDepthC equal to BitDepthY and BitDepthC; decode a slice QP SliceQPY and a offset QpBdOffsetY; derive StrengthControlVal equal to a value of (SliceQpY+QpBdOffsetY)÷(51+QpBdOffsetY) of a first slice of current coded picture; and set StrengthControlVal to an input tensor.

3D video decoding apparatus and 3D video coding apparatus

An arithmetic coding scheme is provided for coding and decoding 3D data and improves coding efficiency for mesh displacements and high-quality coding, and decoding of the 3D data. A 3D data decoding apparatus is also provided for decoding coded data. The apparatus contains an arithmetic decoder that is configured to arithmetically decode a mesh displacement from the coded data. The arithmetic decoder decodes, from the coded data, a first flag indicating whether a coefficient of the mesh displacement has an absolute value greater than 0, a second flag indicating whether the coefficient has an absolute value greater than 1, and a third flag indicating whether the coefficient has an absolute value greater than 2.

3D data decoding apparatus and 3D data coding apparatus

In a case that a scaling value of neural network filter strength is set equal to 0, a decoded image before a deblocking filter is output, and thus block noise occurs. In a case that luma and chroma parameters are not taken into consideration, processing for an image of multiple transfer functions and chroma parameters is not appropriately performed. In a unit of a prescribed block, by using a parameter indicating a degree of application of the NN filter, an image after the deblocking filter and an image after an NN filter are combined using a different ratio of the images. Filter processing of a luma image is switched based on a luma parameter, and filter processing of a chroma image is switched based on a chroma parameter.

A 3D data decoding apparatus for decoding coded data. The 3D data decoding apparatus includes an arithmetic decoder configured to arithmetically decode mesh displacement from the coded data, a context selection unit configured to select a context in the arithmetic decoding, and a context initialization unit configured to set an initial value of the context. In the context initialization unit, a context initialization parameter for initializing the context is decoded from the coded data.

Object There is the problem in the related art that the relationship between a patch size which is a unit of processing of a neural network and the sizes of input and output pictures is not clearly defined. Solution A video decoding apparatus for generating a decoded picture by decoding coded data, the video decoding apparatus comprising:

According to an aspect of the present disclosure, an image decoding apparatus for decoding information specifying a neural network includes: header decoding circuitry that decodes an input tensor identification parameter specifying a process for deriving an input tensor input for a post filter of the neural network. The input tensor identification parameter is a parameter related to a color component channel.

Growing community of inventors

Sakai, Japan

Keiichiro Takada