An image sensor operating in multiple resolution modes including a low resolution mode and a high resolution mode includes a pixel array including a plurality of pixels, wherein each pixel in the plurality of pixels comprises a micro-lens, a first subpixel including a first photodiode, a second subpixel including a second photodiode, and the first subpixel and the second subpixel are adjacently disposed and share a floating diffusion region. The image sensor also includes a row driver providing control signals to the pixel array to control performing of an auto focus (AF) function, such that performing the AF function includes performing the AF function according to pixel units in the high resolution mode and performing the AF function according to pixel group units in the low resolution mode. A resolution corresponding to the low resolution mode is equal to or less than ¼ times a resolution corresponding to the high resolution mode.

Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights determined based, at least in part, on one or more sub-pixel offset values.

An image processing device includes an interface and a control circuit. The interface is configured to receive input line signals in synchronization with input horizontal synchronization signals, respectively. The control circuit is configured to store line image data contained in each of input line signals in the order of reception, generate internal horizontal synchronization signals, and output internal line signals containing the line image data in the input line signals, in synchronization with the internal horizontal synchronization signals, respectively. The input line signals include a first input line signal containing first line image data, and the internal line signals include a first internal line signal containing the first line image data. A horizontal cycle of the internal horizontal synchronization signal corresponding to the first internal line signal is less than a horizontal cycle of the input horizontal synchronization signal corresponding to the first input line signal.

An image processing apparatus includes at least one processor or circuit configured to execute a plurality of tasks including an image acquiring task configured to acquire a first image and a second image that have been obtained by imaging at imaging positions different from each other, an image restoration processing task configured to acquire a first restored image and a second restored image by performing image restoration processing for the first image and the second image respectively, and a pixel increasing processing task configured to acquire a pixel increased image using the first restored image and the second restored image.

An image processing device includes: an image sensor for acquiring a pixel value of each of a plurality pixels; and a controller for acquiring a pattern image including the pixel value of each of the plurality of pixels and an exposure value representing an exposure time, generating a plurality of super resolution images based on pixels having the same exposure value among the plurality of pixels included in the pattern image, generating a motion map, which represents a motion of an object based on a ratio of exposure values of pixels at a selected position among a plurality of pixels included in the plurality of super resolution images and a ratio of pixel values of the pixels at the selected position, and generating a target image according to a weighted sum of the plurality of super resolution images and the motion map.

Provided is an imaging device that performs a pixel shift for moving an imaging element a predetermined shift amount for each exposure to acquire a plurality of images and synthesizes the plurality of images to generate a high-resolution image, the imaging device including: a signal processing unit that sets an image blur correction target value on the basis of a shake of the imaging device detected by a vibration detection unit; and an image blur correction unit that corrects an image blur in accordance with the image blur correction target value, wherein the signal processing unit fixes the image blur correction target value to a predetermined value when the pixel shift is performed.

The present technology relates to a control device, a controlling method, and an imaging apparatus that make it possible to reduce a weight of a movable body while simplifying a structure and to improve control accuracy. A moving body that moves in two or more directions, and a controller that controls movement of the moving body are provided. The controller sets a control value directed to controlling of the movement of the moving body on the basis of an initial position of the moving body and an instructed position of the moving body. A parameter directed to setting of the control value is set on the basis of the initial position and the instructed position. The present technology is applicable, for example, to a shake correction device that corrects a hand shake of an imaging apparatus or a technique that achieves super-resolution by shifting a sensor to capturing a plurality of images.

A camera module according to the present embodiment includes a light emitting part configured to output a light signal to an object, a filter configured to allow the light signal to pass therethrough, at least one lens disposed on the filter and configured to collect the light signal from the object, a sensor configured to generate an electric signal from the light signal collected by the lens, the sensor including a plurality of pixels arranged in an array form, and a tilting part configured to tilt the filter to repeatedly move an optical path of the light signal having passed through the filter according to a predetermined rule. The optical path of the light signal passing through the filter is moved in one direction among diagonal directions of the sensor with respect to an optical path corresponding to the filter being disposed parallel to the sensor.

Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights determined based, at least in part, on one or more sub-pixel offset values.

Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights determined based, at least in part, on one or more sub-pixel offset values.