Abstract: An image processing method includes generating a second image by applying noise to a first image, as a first process, and generating a third image by upsampling the second image through a neural network, as a second process. The second image is generated by applying noise to the first image expressed in a second bit depth higher than a first bit depth of the first image and then restoring the bit depth to the first bit depth.

Abstract: An image processing method includes obtaining a captured image by image capturing using an optical apparatus, and obtaining resolution performance information about a resolution performance of the optical apparatus, and generating an output image by reducing a sampling pitch of the captured image based on the captured image and the resolution performance information, wherein the information indicating the resolution performance is a map, and each pixel of the map indicates the resolution performance of a corresponding pixel of the captured image.

Abstract: An image processing method includes generating, by dividing a first grayscale image, a plurality of second grayscale images where each has less number of pixels than that of the first grayscale image, and generating a plurality of third grayscale images upscaled by inputting the plurality of second grayscale images to a machine learning model.

Abstract: An image processing method includes a first step of acquiring a first image having disparity information and refocus information, and a second step of inputting the first image or the disparity information and the refocus information into a machine learning model, and of generating a second image having an in-focus position different from an in-focus position of the first image based on the refocus information. The refocus information is information on a distance between the in-focus position of the first image and the in-focus position of the second image.

Abstract: An image processing apparatus includes an image acquisition unit configured to acquire a plurality of temporally different images each of which has degraded by a turbulence, a parameter acquisition unit configured to acquire a learned network parameter, and a measurement unit configured to measure a turbulence strength from the plurality of images using the network parameter and a neural network.

Abstract: An image processing apparatus includes a main unit configured to convert an input image into information of a first feature amount using a first convolutional neural network having at least two layers, an input unit configured to convert the input image into information of a second feature amount using a second convolutional neural network, and an output unit configured to convert information of a third feature amount generated by adding the information of the first feature amount and the information of the second feature amount to each other, into an output image using a third convolutional neural network.

Abstract: An image processing method includes generating a second image by applying noise to a first image, as a first process, and generating a third image by upsampling the second image through a neural network, as a second process. The second image is generated by applying noise to the first image expressed in a second bit depth higher than a first bit depth of the first image and then restoring the bit depth to the first bit depth.

Abstract: An image processing apparatus includes at least one processor or circuit configured to execute a plurality of tasks including an acquisition task configured to acquire two first images made by capturing the same object at two different viewpoints, and an image processing task configured to input the two first images into a machine learning model and to estimate a second image at one or more viewpoints different from the two viewpoints.

Abstract: An image processing method includes the steps of acquiring a first image, acquiring a second image that has a noise amount larger than that of the first image and has high frequency components of an object more than those of the first image, and inputting the first image and the second image into a neural network, and generating a third image having the high frequency components of the object more than those of the first image and having the noise amount smaller than that of the second image.

Abstract: An image processing apparatus includes an image acquisition unit configured to acquire a plurality of temporally different images each of which has degraded by a turbulence, a parameter acquisition unit configured to acquire a learned network parameter, and a measurement unit configured to measure a turbulence strength from the plurality of images using the network parameter and a neural network.

Abstract: An image processing apparatus includes a main unit configured to convert an input image into information of a first feature amount using a first convolutional neural network having at least two layers, an input unit configured to convert the input image into information of a second feature amount using a second convolutional neural network, and an output unit configured to convert information of a third feature amount generated by adding the information of the first feature amount and the information of the second feature amount to each other, into an output image using a third convolutional neural network.

Abstract: An image processing method includes the steps of acquiring a first image, acquiring a second image that has a noise amount larger than that of the first image and has high frequency components of an object more than those of the first image, and inputting the first image and the second image into a neural network, and generating a third image having the high frequency components of the object more than those of the first image and having the noise amount smaller than that of the second image.

Abstract: An image processing apparatus includes a weighting unit configured to calculate an error between an estimated image obtained by providing an input image to a convolution neural network and a ground truth image corresponding to the input image and to weight a frequency component of the error, and a parameter setter configured to calculate a gradient based on the weighted error, and to set a network parameter for the convolution neural network.

Abstract: The image processing method includes providing first dictionaries produced by dictionary learning and second dictionaries corresponding to the first dictionaries, performing, on each first dictionary, a process to approximate the first image by linear combination of elements of the first dictionary so as to produce a linear combination coefficient and thereby acquiring multiple linear combination coefficients, and calculating, for each linear combination coefficient, a ratio between a largest coefficient element and a second-largest coefficient element and selecting a specific linear combination coefficient in which the ratio is largest among the multiple linear combination coefficients.

Abstract: The method produces, from a first image, a second image with sparse coding. The method produces, from the first image, a processing intermediate image having a pixel value distribution that a difference among pixel values in a region of the intermediate image is equal to a DC component in a corresponding region of the first image, performs a first process of acquiring, using an AC component in a first region of the intermediate image and a basis produced by dictionary learning, an AC component in a second region, performs a second process of acquiring a difference among pixel values in the second region as a DC component in a corresponding region of the second image, and repeats the first and second processes with changing a position of the first region in the intermediate image to acquire DC components in regions of the second image.

Abstract: The image processing method extracts, from a first image, partial areas such that they overlap one another, and provides, by dictionary learning using model images corresponding to multiple types, a set of linear combination approximation bases and a set of classification bases to acquire classification identification values indicating the multiple types to which each partial area belongs. The method approximates the partial areas by linear combination of the linear combination approximation bases to acquire linear combination coefficients, sets the classification identification values by a linear combination of the classification bases and the linear combination coefficients, sets, for each pixel of the first image, one classification identification value from those set for two or more of the partial areas including that pixel, and produces the second image whose each pixel corresponds to that of the first image and has the one classification identification value.

Abstract: A method includes performing an approximate partially coherent imaging operation for elements of a first basis generated from a model image having no noise and no blur, and generating based upon the first basis a second basis that is blurred, the approximate partially coherent imaging operation being expressed by a convolution integral on an eigenfunction corresponding to a maximum eigenvalue of a Kernel matrix and each element of the first basis, generating an intermediate image in which each pixel value of the observed image that has been denoised is replaced with its square root, and obtaining a restored image by approximating each of a plurality of patches that are set to entirely cover the intermediate image, using a linear combination of elements of the first basis and linear combination coefficients obtained when each patch is approximated by a linear combination of elements of the second basis.

Abstract: A light detecting apparatus includes: a first photoelectric conversion element unit (110) and a second photoelectric conversion element unit (120) each of which converts input light to an electric current and output it; an optical current transducer unit (100) for outputting, as a detected current, a differential current between an electric current outputted by the first photoelectric conversion element unit and an electric current outputted by the second photoelectric conversion element unit; and a first current/voltage converting unit (200) for amplifying the detected current outputted from the optical current transducer unit, converting it to a voltage signal, and outputting the voltage signal.

Abstract: The image processing method includes providing first dictionaries produced by dictionary learning and second dictionaries corresponding to the first dictionaries, performing, on each first dictionary, a process to approximate the first image by linear combination of elements of the first dictionary so as to produce a linear combination coefficient and thereby acquiring multiple linear combination coefficients, and calculating, for each linear combination coefficient, a ratio between a largest coefficient element and a second-largest coefficient element and selecting a specific linear combination coefficient in which the ratio is largest among the multiple linear combination coefficients.

Abstract: The method produces, from a first image, a second image with sparse coding. The method produces, from the first image, a processing intermediate image having a pixel value distribution that a difference among pixel values in a region of the intermediate image is equal to a DC component in a corresponding region of the first image, performs a first process of acquiring, using an AC component in a first region of the intermediate image and a basis produced by dictionary learning, an AC component in a second region, performs a second process of acquiring a difference among pixel values in the second region as a DC component in a corresponding region of the second image, and repeats the first and second processes with changing a position of the first region in the intermediate image to acquire DC components in regions of the second image.