Sony Corporation

Sony Group Corporation

Kenichiro Hosokawa

Takahiro Nagano

Takuro Kawai

Ohji Nakagami

Masashi Uchida

Keisuke Chida

Masaru Ikeda

Kazunori Kamio

Shintaro Okada

Tetsujiro Kondo

Yiwen Zhu

Koji Nishida

Yasuhiko Suga

Kenji Kondo

Hideki Mori

Toshiyuki Sasaki

Yoshiaki Nakamura

Daisuke Kikuchi

Takafumi Morifuji

Takeshi Miyai

Yasuhiro Matsuda

Masatoshi Yokokawa

Takeshi Kunihiro

Takuo Morimura

Shizuo Chikaoka

Hideo Kasama

The present technology relates to an image processing apparatus and method and a program that enable natural representation of light in an image in accordance with a viewpoint. The image processing apparatus calculates information indicating a change in a light source region between an input image and a viewpoint-converted image that is obtained by performing viewpoint conversion on the input image on the basis of a specified viewpoint, and causes a change in representation of light in the viewpoint-converted image on the basis of the calculated information indicating a change in the light source region. The present technology can be applied to an image display system that generates a pseudo stereoscopic image with motion parallax from one image.

Image processing apparatus and method for natural representation of light in an image

The present technology relates to an encoding device, an encoding method, a decoding device, and a decoding method that make it possible to accurately restore an image. The encoding device generates a filter image by performing, on a decoded image locally decoded, filter processing of applying a prediction equation including a second-order or higher higher-order term and performing a product-sum calculation of predetermined tap coefficients and pixels of the decoded image. Moreover, the encoding device encodes an original image by using the filter image. The decoding device decodes coded data included in an encoded bit stream by using a filter image, to generate a decoded image. Moreover, the decoding device generates the filter image by performing, on the decoded image, filter processing of applying a prediction equation. The present technology can be applied to a case where encoding and decoding of an image are performed.

Encoding device, encoding method, decoding device, and decoding method

The encoding apparatus encodes an input image by a non-reversible encoding method and transmits identification information for identifying match components that are, from among a plurality of texture components registered in a database, texture components that match with the input image and encoded data obtained by encoding the input image. The decoding apparatus receives the encoded data and the identification information, decodes the encoded data into a decoded image, and synthesizes the texture component as the match component identified by the identification information from among a plurality of texture components registered in a database and the decoded image. The present technology can be applied, for example, a codec or the like by which an image is encoded and decoded.

Encoding apparatus and encoding method as well as decoding apparatus and decoding method

There is provided an image processing apparatus and an image processing method in which S/N can be improved. A class tap selection unit configures a class tap by selecting a pixel that is a class tap used in class classification of classifying a pixel to be processed of a first image obtained by adding a residual error of prediction encoding and a prediction image together, into any one class of a plurality of classes, from the first image. A class classification unit performs the class classification of the pixel to be processed by using the class tap, and a filter processing unit performs filter processing corresponding to class of the pixel to be processed, with respect to the first image, to generate a second image used in prediction of the prediction image. The class tap selection unit updates a tap structure of the class tap to a selected tap structure.

Image processing apparatus and image processing method

The present disclosure relates to an apparatus and a method for information processing enabling alignment between imaged images to be more accurately performed. With respect to a detection result of a correspondence point between an imaged image including a pattern irradiated for alignment with other imaged image, and the other imaged image including the pattern, an evaluation value with which an occurrence rate of an error in the alignment when the imaged image and the other imaged image are composed with each other is evaluated is calculated; and an irradiated position of the pattern is updated on the basis of the evaluation value calculated. The present disclosure, for example, can be applied to an information processing apparatus, an irradiation device, an imaging apparatus, an irradiation imaging apparatus, a controller, an imaging system or the like.

Information processing apparatus and method

Provided is an encoding apparatus, an encoding method, a decoding apparatus, and a decoding method by which a transmission efficiency and picture quality can be improved. The encoding apparatus encodes an input image by a non-reversible encoding method and transmits identification information for identifying match components that are, from among a plurality of texture components registered in a database, texture components that match with the input image and encoded data obtained by encoding the input image. The decoding apparatus receives the encoded data and the identification information, decodes the encoded data into a decoded image, and synthesizes the texture component as the match component identified by the identification information from among a plurality of texture components registered in a database and the decoded image. The present technology can be applied, for example, to a codec or the like by which an image is encoded and decoded.

The present technology relates to an encoding apparatus and an encoding method as well as a decoding apparatus and a decoding method that make it possible to improve the compression efficiency. The encoding apparatus transmits reduction filter information that reduces tap coefficients for individual ones of a plurality of classes determined by learning that uses a student image equivalent to a first image obtained by addition of a residual of prediction encoding and a prediction image and a teacher image equivalent to an original image corresponding to the first image. The decoding apparatus accepts the reduction filter information and performs prediction arithmetic operation using tap coefficients obtained using the reduction filter information to perform a filter process for the first image to generate a second image. The present technology can be applied, for example, an encoding apparatus and a decoding apparatus of an image.

[Object] To generate a color image with further improved image quality. [Solution] Provided is an image processing device including: an image acquisition unit that acquires a far-infrared image, a near-infrared image, and a visible light image in which a common imaged object is captured; and a generation unit that generates a color image by filtering filter taps including pixels of the far-infrared image, the near-infrared image, and the visible light image.

Image processing based on imaging condition to obtain color image

An image processing apparatus includes a modifying unit configured to modify depth information representing depths in individual pixels of an image in accordance with content included in the image, thereby generating modified depth information, and an enhancing unit configured to perform a stereoscopic effect enhancement process of enhancing a stereoscopic effect of the image by using the modified depth information generated by the modifying unit.

Enhancement of stereoscopic effect of an image through use of modified depth information

There is provided an image processing device including a characteristic estimation portion that, from one of image information obtained from an image sensor and information attached to the image information, estimates a characteristic of the image sensor that is used to generate the image information, and a processing portion that processes the image information in accordance with the characteristic of the image sensor estimated by the characteristic estimation portion.

Image processing device and image processing method, and program

An image processor includes a first acquirer that acquires a matching tap having a target pixel at the center, a second acquirer that acquires plural matching taps each having, at the center, one of pixels in a search area including the pixels surrounding the target pixel, a similarity identifier that identifies, among the matching taps acquired by the second acquirer, a similarity maximizing pixel representing a central pixel of the matching tap having the highest similarity to the matching tap acquired by the first acquirer, and a mixing controller that computes a pixel value of the target pixel by mixing a pixel value obtained by performing a predetermined arithmetic process on pixel values of a prediction tap having the target pixel at the center with a pixel value obtained by performing a predetermined arithmetic process on pixel values of a prediction tap having the similarity maximizing pixel at the center.

Image processing apparatus, image processing method, and program

There is provided an image processing device including a weight calculation unit that calculates a weight corresponding to each of a plurality of pixel values centering on a pixel of interest of an input image based on a feature amount calculated based on the plurality of pixel values centering on the pixel of interest, a regression coefficient reading unit that reads a regression coefficient stored for each class code determined based on a plurality of pixel values corresponding to the pixel of interest of the input image, and a pixel value calculation unit that calculates a pixel value of a pixel of interest of an output image by performing calculation using the plurality of pixel values, the weights, and the regression coefficients centering on the pixel of interest of the input image.

Image processing device and method, learning device and method, and program

In an image processing apparatus, a min-max pixel difference value computing unit computes the difference between the maximum and minimum pixel values in a first image portion including a target pixel and neighbor pixels. A maximum adjacent pixel difference value computing unit computes the maximum value among the difference values between adjacent pixels in the first image portion. An image change feature value computing unit computes a feature value corresponding to the suddenness of image change in the first image portion. A filter coefficient computing unit computes filter coefficients. A sharpen filter accepts, as input, pixels forming a second image portion including the same target pixel as the first image portion and neighbor pixels, and computes an output pixel value for the target pixel.

An image processing apparatus includes a converter converting an interlace image including a first number of pixels into a first progressive image, an interpolator interpolating the first progressive image to generate a second progressive image including a second number of pixels, a classification unit classifying, in accordance with a feature of the second progressive image, into classes, subject pixels forming a third progressive image, which serves as a target image, including the second number of pixels and having a quality higher than the second progressive image, a storage unit storing a prediction coefficient for each of the classes obtained by conducting learning using a plurality of progressive images, each including the second number of pixels, and a computation unit performing computation using the second progressive image and the prediction coefficient for each of the classes to determine the third progressive image from the second progressive image.

Image processing apparatus for converting a lower resolution image into a higher resolution image using cyclic coefficients

An image processing apparatus includes the following elements. A broad-range feature extraction unit extracts broad-range features from pixels located in a predetermined area in relation to a subject pixel of a first image. A broad-range degree-of-artificiality calculator calculates, in a multidimensional space represented by the broad-range features, the broad-range degree of artificiality from the positional relationship of the broad-range features to a statistical distribution range of an artificial image of the first image. A narrow-range feature extraction unit extracts narrow-range features from pixels located in the predetermined area in relation to the subject pixel of the first image. A narrow-range degree-of-artificiality calculator calculates, in a multidimensional space represented by the narrow-range features, the narrow-range degree of artificiality from the positional relationship of the narrow-range features to a statistical distribution range of the artificial image. A degree-of-artificiality calculator calculates the degree of artificiality of the subject pixel.

Growing community of inventors

Kanagawa, Japan

Kenichiro Hosokawa