Nippon Telegraph and Telephone Corporation

Shinobu Kudo

Atsushi Shimizu

Masaki Kitahara

Shota Orihashi

Ryuichi Tanida

Hiroshi Fujii

Mayuko Watanabe

An encoding device includes: an association processing unit that associates first encoded data which is encoded data of an original image with second encoded data which is encoded data of a decoded image which is a result of decoding of the encoded data of the original image; and an encoding unit that encodes, based on the result of associating the first encoded data with the second encoded data, a target image which is an image to be encoded.

Encoding apparatus, encoding method, and program

A coding apparatus is a coding apparatus for coding an original image and includes: a division section that divides the original image into blocks that are a plurality of areas to acquire the plurality of blocks; a determination section that, for each of the blocks, determines whether or not to determine the block as an interpolation target; and a substitution section that substitutes a value of a pixel included in the block determined as the interpolation target, with a value that decreases a code amount of the block determined as the interpolation target. The determination section determines whether or not to determine the area that is a target of the determination as an area that is the interpolation target, using an evaluation based on an accuracy of prediction of an image of the block by intra prediction or inter prediction and a degree of the area that is the interpolation target being a generated one.

An image processing apparatus for performing correction for each frame group including a predetermined number of frames into which video data is divided includes a decoding unit configured to obtain a corrected frame group by correcting a second frame group, which is a frame group continuous with a first frame group in time, using a feature quantity of the first frame group. The decoding unit performs the correction so that subjective image quality based on a relationship between the second frame group and a frame group subsequent to the second frame group in time is increased and so that a predetermined classifier classifies that a frame group in which the second frame group is concatenated with the frame group subsequent to the second frame group in time is the same as a frame group in which the corrected frame group is concatenated with a corrected frame group obtained by correcting the frame group subsequent to the second frame group in time.

Image processing apparatus, image processing method and image processing program

A coding device of the present invention for coding an image includes: a region acquiring unit configured to acquire a region of a first image that matches a predetermined condition; an image acquiring unit configured to obtain a second image by associating the first image, the acquired region, and a region obtained by removing the acquired region from the first image with each other; and a coding unit configured to code the second image. Also, an image interpolation system of the present invention for interpolating a first image includes: an acquiring unit configured to acquire the first image and auxiliary information by associating a second image, a matching region of the second image that matches a predetermined condition, and a region obtained by removing the matching region from the second image with each other; and an interpolating unit configured to interpolate the first image using the auxiliary information, and obtain an image that approximates the second image. With the present invention, it is possible to execute image interpolation processing while suppressing degradation of the subjective image quality.

Encoding apparatus, image interpolating apparatus and encoding program

A code amount estimation device includes a code amount estimation unit configured to estimate a first target code amount on the basis of a first code amount estimation area in first image information and a code amount estimation model for estimating the first target code amount for each first code amount estimation area using the first code amount estimation area and multiple first quantization parameters determined in advance, and the code amount estimation model is a model generated by associating a second code amount estimation area in second image information, multiple second quantization parameters, and a second target code amount for each second code amount estimation area when coding is performed with respective values of multiple second quantization parameters with each other.

Code amount estimation device, code amount estimation method, and code amount estimation program

The computational complexity when a block configuration in an encoding target region is determined is reduced while the degradation of coding efficiency is suppressed. A video encoding apparatus includes a block selecting unit which selects each of blocks obtained by recursively dividing an encoding target block as a target block in a predetermined sequence, a block size acquiring unit which acquires the smallest block size in an adjacent block for the selected target block, an evaluation value calculating unit which calculates an evaluation value of the target block if a block size of the target block matches any one of the acquired block size, the block size one level higher than the acquired block size, and the block size one level lower than the acquired block size, and a block configuration determining unit which determines a combination of the blocks constituting the region within the encoding target block based on the evaluation value.

Growing community of inventors

Yokosuka, Japan

Shinobu Kudo