The subject technology provides a framework for learning neural scene representations directly from images, without three-dimensional (3D) supervision, by a machine-learning model. In the disclosed systems and methods, 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. For example, a loss function can be provided which enforces equivariance of the scene representation with respect to 3D rotations. Because naive tensor rotations may not be used to define models that are equivariant with respect to 3D rotations, a new operation called an invertible shear rotation is disclosed, which has the desired equivariance property. In some implementations, the model can be used to generate a 3D representation, such as mesh, of an object from an image of the object.

A recognition processing section performs subject recognition in a processing area of an image obtained by an imaging section. The recognition processing section determines an image characteristic of the processing area on the basis of a characteristic map indicating an image characteristic of the image obtained by the imaging section and uses a recognizer corresponding to the image characteristic of the processing area. The characteristic map includes a map based on an optical characteristic of an imaging lens used in the imaging section and is stored in a characteristic information storage section. An imaging lens has a winder angle of view in all directions or in a predetermined direction than a standard lens, and the optical characteristic thereof differs depending on a position on the lens. The recognition processing section performs the subject recognition using a recognizer corresponding to resolution or skewness of the processing area, for example.

Electronically derotating a picture-in-picture video source can be used to independently derotate a secondary video source separate a primary video source. A method of electronically derotating a picture-in-picture image are described herein, the method comprising processing a first image having a first image primary axis; processing a second image having a second image primary axis; derotating the second image around the second image primary axis to align the second image primary axis substantially parallel with the first image primary axis; and displaying the first image and the second image on a display.

Systems and methods for digitized document image data spillage recovery are provided. One or more memories may be coupled to one or more processors, the one or more memories including instructions operable to be executed by the one or more processors. The one or more processors may be configured to capture an image; process the image through at least a first pass to generate a first contour; remove a preprinted bounding region of the first contour to retain text; generate one or more pixel blobs by applying one or more filters to smudge the text; identify the one or more pixel blobs that straddle one or more boundaries of the first contour; resize the first contour to enclose spillage of the one or more pixel blobs; overlay the text from the image within the resized contour; and apply pixel masking to the resized contour.

A material data collection system allows capturing of material data. For example, the material data collection system may include digital image data for materials. The material data collection system may ensure that captured digital image data is properly aligned, so that material data may be easily recalled for later use, while maintaining the proper alignment for the captured digital image. The material data collection system may include using a capture guide, to provide cues on how to orient a mobile device used with the material data collection system.

An optical imaging system for imaging a target during a medical procedure, the optical imaging system involving a first camera for capturing a first image of the target, a second wide-field camera for capturing a second image of the target, at least one optional path folding mirror disposed in an optical path between the target and a lens of the second camera, and a processor for receiving the first image and the second image, the processor configured to apply an image transform to one of the first image and the second wide-field image and combine the transformed image with the other one of the images to produce a stereoscopic image of the target.

Systems and methods for spatial analysis of analytes are provided. A data structure is obtained comprising an image, as an array of pixel values, of a sample on a substrate having a identifier, fiducial markers and a set of capture spots. The pixel values are used to identify derived fiducial spots. The substrate identifier identifies a template having reference positions for reference fiducial spots and a corresponding coordinate system. The derived fiducial spots are aligned with the reference fiducial spots using an alignment algorithm to obtain a transformation between the derived and reference fiducial spots. The transformation and the template corresponding coordinate system are used to register the image to the set of capture spots. The registered image is then analyzed in conjunction with spatial analyte data associated with each capture spot, thereby performing spatial analysis of analytes.

Systems, apparatuses, and methods are described for allowing a motion-detecting system to distinguish and/or mask motion that originates from a display screen. One method includes: capturing, by a computing device associated with a motion detector, an image of a field of view of the motion detector. The computing device may determine, based on object recognition, one or more candidate display areas within the image of the field of view. Based on the determined candidate display areas within the image, the computing device may generate a mask corresponding to the field of view. The computing device may exclude, from motion detection, motion occurring within the mask of the field of view.

Generating a table with at least one skewed row, skewed column, shifted row, or shifted column is described. A table generation system generates a table that includes cells arranged in a grid comprising rows and columns, and defines each cell using a grid address, a grid span, a grid angle, a string skew value, a string shift value, and a shift indicator for the cell. The table generation system may receive input modifying a grid angle for at least one row or column and generate a modified table by skewing cells included in the at least one row or column by the grid angle. The table generation system may additionally or alternatively receive input shifting at least one row or column by a string shift value and modify the display of the table by shifting the at least one row or column according to the string shift value.

A material data collection system allows capturing of material data. For example, the material data collection system may include digital image data for materials. The material data collection system may ensure that captured digital image data is properly aligned, so that material data may be easily recalled for later use, while maintaining the proper alignment for the captured digital image. The material data collection system may include using a capture guide, to provide cues on how to orient a mobile device used with the material data collection system.