Abstract: According to an aspect of the present invention, there is provided a learning device including: a classification unit that classifies latent variables obtained from learning data used for learning into a label feature quantity and a non-label feature quantity; a decoding unit that decodes the label feature quantity and the non-label feature quantity classified by the classification unit by using decoder parameters to generate reconstruction data; and an optimization unit that optimizes the decoder parameters to minimize a classification error between the label feature quantity and label information used for classification by using the label feature quantity, and minimize a reconstruction error by using the label feature quantity and the non-label feature quantity.

Abstract: According to an aspect of the present invention, there is provided a learning device including: a classification unit that classifies latent variables, which are feature quantities obtained from learning data used for learning, by using a label feature quantity having label information used for classification; a decoding unit that decodes the latent variables to generate reconstruction data by using predetermined decoding parameters; and an optimization unit that optimizes the decoding parameters to minimize a classification error between the label feature quantity and the label information by using the label feature quantity.

Abstract: One aspect of the present invention is a data generation method which generates data based on a predetermined estimation model, the data generation method includes a generation step of generating data estimated as a predetermined label by the estimation model and provided with the predetermined label, and generated data has at least either one of a feature close to data to which a label different from the predetermined label is imparted or a feature different from known data to which the predetermined label is imparted.

Abstract: A parameter optimization method includes extracting a feature vector using input data, acquiring a classification result of the feature vector and a class representative vector of every class serving as a classification target, and optimizing a parameter used in the extracting based on a classification error obtained using correct answer data and the classification result and a distance error between the class representative vectors such that areas of features of the classes in a feature space do not overlap each other.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A generation apparatus includes an interpolation unit that generates, from a moving image including a plurality of frames, an interpolated frame in which some regions in one or more frames included in the moving image are interpolated, and a discrimination unit that discriminates whether a plurality of input frames is interpolated frames in which some regions in the plurality of input frames is interpolated. The discrimination unit includes a temporal direction discrimination unit that discriminates time-wise the plurality of input frames, a spatial direction discrimination unit that discriminates space-wise the plurality of input frames, and an integrating unit that integrates discrimination results from the temporal direction discrimination unit and the spatial direction discrimination unit.

Abstract: An encoding apparatus encodes an input image and includes: a provisional encoded data acquisition unit configured to obtain provisional encoded data which has a size greater than a target size of encoded data which is data obtained by encoding the image based on the image and a parameter for determining the target size; and an encoded data acquisition unit configured to obtain the encoded data by converting data within a data range outside of a data range corresponding to the target size in the provisional encoded data into a predetermined value. The provisional encoded data acquisition unit obtains the provisional encoded data so that features for determining the image are contained more within the data range corresponding to the target size than in the data range outside of the data range corresponding to the target size.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.