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.

Implementations generally increase the virtual resolution of a camera sensor. In some implementations, a method includes moving an image sensor in a predetermined pattern, wherein the image sensor includes an array of light collecting elements, and wherein each light collecting element of the sensor array cycles through a plurality of positions in the predetermined pattern. The method further includes capturing a plurality of samples of light at each light collecting element, wherein each light collecting element captures a plurality of the samples in a cycle of movement in the predetermined pattern. The method further includes converting each sample captured at each position into a value. The method further includes generating at least one image from an aggregate of values converted from the samples of light.

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.

A solid-state imaging element that detects address events captures high-quality images. The solid-state imaging element includes a pixel array section that has a plurality of pixels including a specific pixel arranged in a two-dimensional lattice pattern. The specific pixel includes a pixel circuit and two analog-digital converters. The pixel circuit outputs two analog signals proportional to an amount of charge produced by photoelectric conversion. The analog-digital converters convert the respective two analog signals into digital signals with different resolutions.

A solid-state imaging element that detects address events captures high-quality images. The solid-state imaging element includes a pixel array section that has a plurality of pixels including a specific pixel arranged in a two-dimensional lattice pattern. The specific pixel includes a pixel circuit and two analog-digital converters. The pixel circuit outputs two analog signals proportional to an amount of charge produced by photoelectric conversion. The analog-digital converters convert the respective two analog signals into digital signals with different resolutions.

An image processing device includes one or more processors configured to: generate a high-resolution combined image by aligning the plurality of images with each other in a high-resolution image space based on an amount of displacement between the plurality of images, and combining the plurality of images; generate at least two low-resolution combined images by generating at least two groups each composed of at least two images by dividing the plurality of images in the time direction, aligning the at least two images in each of the groups with each other in a low-resolution image space based on the amount of displacement, and combining the at least two images through weighted addition; calculate, in each region, a feature quantity pertaining to a correlation between the generated at least two low-resolution combined images; and correct the high-resolution combined image based on the calculated feature quantity.

A solid-state imaging element that detects address events captures high-quality images. The solid-state imaging element includes a pixel array section that has a plurality of pixels including a specific pixel arranged in a two-dimensional lattice pattern. The specific pixel includes a pixel circuit and two analog-digital converters. The pixel circuit outputs two analog signals proportional to an amount of charge produced by photoelectric conversion. The analog-digital converters convert the respective two analog signals into digital signals with different resolutions.

A microscope system is provided with a microscope that acquires images at least at a first magnification and a second magnification higher than the first magnification, and a processor. The processor is configured to specify a type of a container in which a specimen is placed, and when starting observation of the specimen placed in the container at the second magnification, the processor is configured to specify a map region corresponding to a map image constructed by stitching together a plurality of second images acquired by the microscope at a higher magnification than the first magnification by performing object detection according to the type of the container on a first image that includes the container acquired by the microscope at the first magnification, and cause a display unit to display the first image and a range of the map region on the first image.

A camera module according to an embodiment includes an image sensor configured to output a plurality of image frames; a lens assembly disposed on the image sensor, the lens assembly forming an optical path of light incident on the image sensor from outside; a controller configured to generate a control signal to adjust at least one of the optical path of the lens assembly or the position of the image sensor relative to the lens assembly; and an image synthesizer configured to synthesize the plurality of image frames to generate a composite image, wherein the composite image has a higher resolution than the plurality of image frames, and wherein the plurality of image frames are respective image frames generated along respectively different optical paths changed by the lens assembly or respective image frames generated by change in the position of the image sensor relative to the lens assembly.

A camera module according to an embodiment of the present invention includes a lighting unit configured to output an incident light signal to be emitted to an object, a lens unit configured to concentrate a reflected light signal reflected from the object, an image sensor unit configured to generate electric signals from the reflected light signal concentrated by the lens unit, a tilting unit configured to shift an optical path of at least one of the incident light signal and the reflected light signal for each image frame in units of subpixels of the image sensor unit, and an image control unit configured to extract depth information of the object using a phase difference between the incident light signal and the reflected light signal. The image control unit includes an image controller configured to extract the depth information having a higher resolution than a plurality of subframes generated using the electric signals on the basis of the subframes.