A method of image processing in a structured light imaging device is provided that includes capturing a plurality of images of a scene into which a structured light pattern is projected by a projector in the structured light imaging device, extracting features in each of the captured images, finding feature matches between a reference image of the plurality of captured images and each of the other images in the plurality of captured images, rectifying each of the other images to align with the reference image, wherein each image of the other images is rectified based on feature matches between the image and the reference image, combining the rectified other images and the reference image using interpolation to generate a high resolution image, and generating a depth image using the high resolution image.

An information processing apparatus having: a display control unit configured to display a plurality of virtual viewpoint images respectively corresponding to a plurality of virtual viewpoints on a display unit, wherein each of the plurality of virtual viewpoint images is generated based on image data obtained by a plurality of image capturing apparatuses performing image capturing from different directions; a reception unit configured to receive an input in accordance with a user operation for changing a virtual viewpoint corresponding to one virtual viewpoint image of the plurality of virtual viewpoint images displayed on the display unit; and a viewpoint control unit configured to perform control to change a plurality of virtual viewpoints respectively corresponding to the plurality of virtual viewpoint images based on the received input.

Systems, devices, and techniques related to matching features between a dynamic vision sensor and one or both of a dynamic projector or another dynamic vision sensor are discussed. Such techniques include casting a light pattern with projected features having differing temporal characteristics onto a scene and determining the correspondence(s) based on matching changes in detected luminance and temporal characteristics of the projected features.

A method for selecting an operation mode of a mobile platform includes detecting a height grade of the mobile platform and selecting an operation mode of the mobile platform according to a result of the detecting.

An image output apparatus comprising an output control unit configured to output region annotation information including region information indicating a region included in an image and annotation information indicating information on the region, the region annotation information being superimposed on the image, wherein when a plurality of pieces of the region annotation information are superimposed on the image, the output control unit superimposes first region annotation information associated with a first region with a first depth closer to the front than second region annotation information associated with a second region with a second depth that has larger depth than the first depth.

A hole filling method for providing a virtual three-dimensional (3D) model, the hole filling method being executable on a computing device and including: acquiring an original learning image and a hole generation learning image for the original learning image, wherein the hole generation learning image is an image in which at least one hole is generated based on the original learning image; generating a hole filling learning image by performing hole filling on the hole generation learning image by using a neural network; performing a spherical transformation on each of the hole filling learning image and the original learning image; and training the neural network based on a difference between the spherically-transformed hole filling learning image and the spherically-transformed original learning image.

Systems and methods for three-dimensional imaging are disclosed. A three-dimensional imaging system may include a light source to emit a light pulse. The divergence of the light pulse may be configurable by the system. For example, the system may also include a receiving lens having a field of view and configured to receive a portion of the light pulse reflected or scattered by a scene. The system may configure the light source so that the divergence of the light pulse matches or approximates the field of view of the receiving lens.

Features for a lightweight stereoscopic viewing client are described. The client can generate accurate ground point coordinates from selections within the lightweight viewer by accumulating the transformations from original image sources to the images used to render the stereoscopic scene to accurately predict error for a point selection. The viewer may also be decoupled from a permanent image store allowing on-demand retrieval of images via a network for stereoscopic viewing.

A method and system for encoding a stereoscopic image pair is disclosed. Groups of pixels are analyzed to determine the depth of each pixel group. The number of bits per pixel used to encode each pixel group is selected based on the depth of that pixel group. Therefore, images of objects closer to the camera pair, which appear closer to the viewer, are encoded with a larger number of bits per pixel than objects perceived to be farther from the viewer. The number of bits per pixel may also be increased based on a number of objects depicted or motion detected. The size of prediction blocks used to encode image portions may also be determined based on an angular distance of an image portion relative to the center of the frame. Therefore, smaller prediction blocks may be used to encode image portions closer to the center of the frame.

A remote operation apparatus is configured to operate in response to a control signal transmitted via a network from a user apparatus connected to a display unit and includes a movable unit capable of changing a posture. The remote operation apparatus includes: a video data acquisition unit configured to acquire video data acquired from a camera disposed in the movable unit; a motion detection data acquisition unit configured to acquire, through a motion sensor, motion detection data representing a change in the posture of the movable unit; and a data transmission unit configured to transmit the acquired video data and the acquired motion detection data to the user apparatus via the network.