Abstract: A method includes sharpening a first image to generate a second image, generating a first weight map based on the first image, generating a second weight map based on the second image, and generating a third image based on the first image, the second image, the first weight map, and the second weight map, wherein each of the first weight map and the second weight map indicate a weight of one of the first image and the second image in the generation of the third image.

Abstract: A manufacturing method of learning data is used for making a neural network perform learning. The manufacturing method of learning data includes a first acquiring step configured to acquire an original image, a second acquiring step configured to acquire a first image as a training image generated by adding blur to the original image, and a third acquiring step configured to acquire a second image as a ground truth image generated by adding blur to the original image. A blur amount added to the second image is smaller than that added to the first image.

Abstract: A manufacturing method of learning data is used for making a neural network perform learning. The manufacturing method of learning data includes a first acquiring step configured to acquire an original image, a second acquiring step configured to acquire a first image as a training image generated by adding blur to the original image, and a third acquiring step configured to acquire a second image as a ground truth image generated by adding blur to the original image. A blur amount added to the second image is smaller than that added to the first image.

Abstract: A manufacturing method of learning data is used for making a neural network perform learning. The manufacturing method of learning data includes a first acquiring step configured to acquire an original image, a second acquiring step configured to acquire a first image as a training image generated by adding blur to the original image, and a third acquiring step configured to acquire a second image as a ground truth image generated by adding blur to the original image. A blur amount added to the second image is smaller than that added to the first image.

Abstract: An image processing apparatus includes an acquirer configured to acquire a captured image generated through imaging by an optical system, a reconstruction processor configured to reconstruct a discretized point spread function of the optical system using coefficient data used to approximate the point spread function, and a sharpening processor configured to perform unsharp mask processing for the captured image based on information on the reconstructed point spread function. A discretization interval of the reconstructed point spread function is different according to an image height.

Abstract: An image processing apparatus includes an acquirer configured to acquire a captured image generated through imaging by an optical system, a reconstruction processor configured to reconstruct a discretized point spread function of the optical system using coefficient data used to approximate the point spread function, and a sharpening processor configured to perform unsharp mask processing for the captured image based on information on the reconstructed point spread function. A discretization interval of the reconstructed point spread function is different from a pixel pitch in an image sensor used for the imaging.

Abstract: An image processing method includes the steps of acquiring a captured image generated through image capturing using an optical system, performing first shaping processing so as to reduce a difference between a maximum value and a non-maximum value for data generated using information of a point spread function of the optical system corresponding to an image capturing condition of the captured image, performing rotating processing according to a position of the captured image for the data after the first shaping processing, and performing sharpening processing of the captured image using the data after the rotating processing.

Abstract: An image processing apparatus includes an acquirer configured to acquire a captured image generated through imaging by an optical system, a reconstruction processor configured to reconstruct a discretized point spread function of the optical system using coefficient data used to approximate the point spread function, and a sharpening processor configured to perform unsharp mask processing for the captured image based on information on the reconstructed point spread function. A discretization interval of the reconstructed point spread function is different according to an image height.

Abstract: An image processing apparatus includes an acquirer configured to acquire a captured image generated through imaging by an optical system, a reconstruction processor configured to reconstruct a discretized point spread function of the optical system using coefficient data used to approximate the point spread function, and a sharpening processor configured to perform unsharp mask processing for the captured image based on information on the reconstructed point spread function. A discretization interval of the reconstructed point spread function is different from a pixel pitch in an image sensor used for the imaging.

Abstract: The image processing apparatus is configured to perform image processing on an input image produced by image capturing through an optical system. The apparatus includes a first distribution producer configured to produce a first distribution by using data for approximating a point spread function that corresponds to a condition relating to the image capturing, a second distribution producer configured to produce a second distribution by mirroring a part of the first distribution, a filter producer configured to produce, by using the second distribution, a first filter to be used for a sharpening process, and a processor configured to perform the sharpening process on the input image by using the first filter to produce a sharpened image.

Abstract: An image processing method includes the steps of acquiring a captured image generated through image capturing using an optical system, performing first shaping processing so as to reduce a difference between a maximum value and a non-maximum value for data generated using information of a point spread function of the optical system corresponding to an image capturing condition of the captured image, performing rotating processing according to a position of the captured image for the data after the first shaping processing, and performing sharpening processing of the captured image using the data after the rotating processing.

Abstract: An image processing apparatus acquires an input image generated by image pickup via an optical system, and perform unsharp mask processing for the input image using a filter generated based on information of a PSF of the optical system. The filter is generated based on an unsharp mask used for the unsharp mask processing, and includes two-dimensional data having filter coefficients that are arranged rotationally asymmetrically with respect to a filter coefficient corresponding to a target pixel in the input image in convoluting the filter with the input image. A peak position or a center of gravity position of the unsharp mask accords with a position of the filter coefficient corresponding to the target pixel in the filter.

Abstract: An image processing apparatus includes a processor that sharpens an input image on the basis a difference between a filter and a low pass filter, which are generated using of information regarding a point spread function of an optical system corresponding to an image pickup condition of the optical system, or a difference between an image obtained by applying the filter to an input image generated by imaging through the optical system and an image obtained by applying the low pass filter to the input image.

Abstract: A non-transitory computer-readable storage medium storing an image processing program that causes a computer to execute an image processing method comprising acquiring step of acquiring an input image generated by image pickup through an optical system, generating step of generating a point spread function by using coefficient data of a function approximating a point spread function corresponding to an image-pickup condition of the optical system, and providing step of providing unsharp mask processing to the input image using a filter generated based on information of the point spread function generated by using the coefficient data. The filter is a filter having two-dimensional data.

Abstract: An image processing apparatus includes a processor that sharpens an input image on the basis a difference between a filter and a low pass filter, which are generated using of information regarding a point spread function of an optical system corresponding to an image pickup condition of the optical system, or a difference between an image obtained by applying the filter to an input image generated by imaging through the optical system and an image obtained by applying the low pass filter to the input image.

Abstract: An image processor includes a correction signal generator configured to generate a correction signal by calculating a difference between an image and an image obtained by applying an unsharp mask generated based on a PSF corresponding to an image-pickup conditions of an image-pickup optical system to the image, and a correction signal applier configured to sharpen the image by multiplying the correction signal generated by the generator by a constant and by adding a multiplied correction signal to the image.

Abstract: The image processing apparatus is configured to perform image processing on an input image produced by image capturing through an optical system. The apparatus includes a first distribution producer configured to produce a first distribution by using data for approximating a point spread function that corresponds to a condition relating to the image capturing, a second distribution producer configured to produce a second distribution by mirroring a part of the first distribution, a filter producer configured to produce, by using the second distribution, a first filter to be used for a sharpening process, and a processor configured to perform the sharpening process on the input image by using the first filter to produce a sharpened image.

Abstract: The image processing apparatus performs an image process on a first image produced by image capturing. The apparatus includes: a memory storing coefficient data containing coefficients to be used in an approximation function to approximate a PSF of an image capturing optical system, and a processor performs the image process. The processor produces an approximated point spread function by using the coefficient of the coefficient data corresponding to an optical state of the optical system in the image capturing and two of a pixel pitch of an image sensor, a kernel size of a filter to be used for a sharpening process on the first image and number of taps of the filter; produce the filter by using the approximated PSF; and produce a second image that is a sharpened image by applying the filter to the first image.

Abstract: An image processor includes a correction signal generator configured to generate a correction signal by calculating a difference between an image and an image obtained by applying an unsharp mask generated based on a PSF corresponding to an image-pickup conditions of an image-pickup optical system to the image, and a correction signal applier configured to sharpen the image by multiplying the correction signal generated by the generator by a constant and by adding a multiplied correction signal to the image.

Abstract: An image processor includes a correction signal generator configured to generate a correction signal by calculating a difference between an image and an image obtained by applying an unsharp mask generated based on a PSF corresponding to an image-pickup conditions of an image-pickup optical system to the image, and a correction signal applier configured to sharpen the image by multiplying the correction signal generated by the generator by a constant and by adding a multiplied correction signal to the image.