Abstract: There is provided with an image processing apparatus that generates learning data for use in machine learning using a model. An obtaining unit is configured to obtain a first image for use in learning by the model. A generating unit is configured to, in a case where a first luminance of the first image is greater than a threshold, generate a second image with a second luminance different to the first luminance.

Abstract: An image processing apparatus comprises a first obtaining unit configured to obtain a restoration accuracy of processing for restoring a teacher image from a deteriorated image for which deterioration has been added to the teacher image, a second obtaining unit configured to obtain a frequency characteristic of the teacher image, and a first training unit configured to perform processing for training a learning model based on the restoration accuracy and the frequency characteristic.

Abstract: In the present disclosure, an appropriate inference is made using a recurrent-type neural network in image restoration processing. An input-image-acquisition unit acquires input image data. A learning-parameter-acquisition unit acquires a learning parameter to learn an image restoration network. An initialization determination unit acquires learning-sequence-length-information from the learning parameter and generates initialization information specifying a frame where two degradation restoration units perform initialization. Each degradation restoration unit receives one frame (current frame) of the input image data, sees the initialization information, determines whether to initialize recurrent information in a current frame inference, makes an inference about the current frame using initial image data or an inference result about a preceding frame immediately before the current frame as recurrent information, and outputs the inference result to a synthesis unit and the degradation restoration unit itself.

Abstract: An object of the technique of the present disclosure is to obtain a demosaic network whose robustness for noise is high. In the technique of the present disclosure, first, a data set including a set of a teacher image with noise and a pupil image with noise is generated. Then, learning of a demosaic network is performed by using an image pair of the teacher image with noise and the pupil image with noise, to both of which noise is added.

Abstract: In an image processing system in which development processing is applied to a RAW image in a server apparatus and results thereof are provided to a client terminal, the capacity of image data that is transmitted to the client terminal is reduced. The client terminal applies low-load development processing to an input RAW image and stores and displays the results image thereof. On the other hand, the server generates a difference image between both results images by applying the low-load and high-load development processing and provides the difference image to the client terminal. Then, based on the difference image, the client terminal reproduces a results image of the high-load development processing.

Abstract: An image processing apparatus obtains a first image of an object based on image capturing by an image capturing apparatus, obtains a parameter concerning a resolution of the first image, and generates a second image of the object having a resolution higher than the resolution of the first image in response to input of input data including the obtained first image and the obtained parameter.

Abstract: An image processing apparatus includes an acquisition unit configured to acquire training image data, an extraction unit configured to learn the training image data and extract first difficult image data that is difficult to learn from a result of the learning, a generation unit configured to generate student image data by mosaicking the first difficult image data, and a training unit configured to generate a network parameter obtained by re-learning a pair of the first difficult image data and the student image data. The training unit repeats the re-learning by generating a plurality of times second difficult image data different from the first difficult image data.

Abstract: There is provided with an image processing apparatus that generates learning data for use in machine learning using a model. An obtaining unit is configured to obtain a first image for use in learning by the model. A generating unit is configured to, in a case where a first luminance of the first image is greater than a threshold, generate a second image with a second luminance different to the first luminance.

Abstract: An image processing apparatus comprises an acquisition unit configured to acquire a probability distribution of a color in a teacher image group, a generation unit configured to generate, as an artificial teacher image, an image having a color sampled based on the probability distribution, and a learning unit configured to perform learning of a learning model for performing a demosaicking inference, by using the artificial teacher image.

Abstract: In an image processing system in which development processing is applied to a RAW image in a server apparatus and results thereof are provided to a client terminal, the capacity of image data that is transmitted to the client terminal is reduced. The client terminal applies low-load development processing to an input RAW image and stores and displays the results image thereof. On the other hand, the server generates a difference image between both results images by applying the low-load and high-load development processing and provides the difference image to the client terminal. Then, based on the difference image, the client terminal reproduces a results image of the high-load development processing.

Abstract: The image processing apparatus has: an image acquisition unit configured to acquire a captured image of an image capturing area in which an object is located; a determination unit configured to determine parameters to be used for image processing to improve resolution of an image of the object, by learning using a dataset of images of the object, wherein the dataset is generated based on object information indicating a degree of importance of the object; and a processing unit configured to perform the image processing to improve the resolution of an image of the object included in the acquired captured image, using the parameters determined by the determination unit.

Abstract: An object of the technique of the present disclosure is to obtain a demosaic network whose robustness for noise is high. In the technique of the present disclosure, first, a data set including a set of a teacher image with noise and a pupil image with noise is generated. Then, learning of a demosaic network is performed by using an image pair of the teacher image with noise and the pupil image with noise, to both of which noise is added.

Abstract: An image processing apparatus obtains a first image of an object based on image capturing by an image capturing apparatus, obtains a parameter concerning a resolution of the first image, and generates a second image of the object having a resolution higher than the resolution of the first image in response to input of input data including the obtained first image and the obtained parameter.

Abstract: An image processing apparatus 106 obtains a captured image captured by an image capturing device 102 in an input image obtaining unit 501. A foreground background separating unit 503 obtains a foreground input image 302 by separating a foreground area including a specific object from the obtained captured image. By inputting the foreground input image 302 to a resolution enhancing unit 506, a foreground output image 306 having a higher resolution as compared to the foreground input image 302 is outputted from the resolution enhancing unit 506. The foreground output image 306 is used to generate a virtual viewpoint image.

Abstract: The image processing apparatus has: an image acquisition unit configured to acquire a captured image of an image capturing area in which an object is located; a determination unit configured to determine parameters to be used for image processing to improve resolution of an image of the object, by learning using a dataset of images of the object, wherein the dataset is generated based on object information indicating a degree of importance of the object; and a processing unit configured to perform the image processing to improve the resolution of an image of the object included in the acquired captured image, using the parameters determined by the determination unit.