A pose estimation training system includes: a first model configured to generate a first 6 degrees of freedom (DoF) pose of a first camera that captured a first image from a first domain; a second model configured to generate a second 6 DoF pose of a second camera that captured a second image from a second domain, where the second domain is different than the first domain; a discriminator module configured to, based on first and second outputs from the first and second encoder modules, generate a discriminator output indicative of whether the first and second images are from the same domain; and a training control module configured to, based on the discriminator output, selectively adjust at least one weight value shared by the first model and the second model.

Systems and methods for predicting images with enhanced spatial resolution using a neural network are provided herein. According to an aspect of the invention, a method includes accessing an input image of a biological sample, wherein the input image includes a first spatial resolution and a plurality of spectral images, and wherein each spectral image of the plurality of spectral images includes data from a different wavelength band at a different spectral channel; applying a trained artificial neural network to the input image; generating an output image at a second spatial resolution, wherein the second spatial resolution is higher than the first spatial resolution, and wherein the output image includes a fewer number of spectral channels than the plurality of spectral images included in the input image; and outputting the output image.

Embodiments of the present disclosure relate performing registration of a first image to a second image where the first image is undistorted to linear space before applying a geometric transformation matrix to modify the first image to align with the second image. The geometric transformation matrix may be a linear matrix that causes the undistorted version of the first image to make translation movement, rotational movement or both. The undistorted and modified first image is then reverted back to nonlinear distorted space. Then the reverted first image may be warped to better align with the second image for fusing with the second image. In this way, visual distortions in the fused image such as wobbling may be reduced or eliminated.

An encoder may generate, for each of a plurality of block vectors, an intra block compensated prediction of a block. The encoder may select, based on the intra block compensated predictions of the block, a block vector from the plurality of block vectors for the block. The encoder may determine affine transform parameters of the intra block compensated prediction for the block vector. The encoder may signal, in a bit stream, both of an indication of an affine transform of the intra block compensated prediction and the affine transform parameters based on a residual determined for the intra block compensated prediction generated for the block vector and a value of the affine transform parameters.

A method of generating a composite image from multiple images captured for a subject is disclosed. In some embodiments, the method may include receiving, via an image capturing device, a plurality of sets of images of at least a portion of a subject. The images within a set of images may be captured at a plurality of vertical positions with respect to an associated fixed section of a horizontal plane. The method may further include generating a plurality of focus-stacked images corresponding to the plurality of sets of images, for example, by combining the images in the associated set of images. The method may further include aligning the plurality of focus-stacked images in the horizontal plane based on a horizontal coordinate transformation model to generate a composite image representing the subject.

Techniques related to performing image registration are discussed. Such techniques include converting a source image region and a target image portion from a color image space to a semantic space and iteratively converging homography parameters using the source image region and target image portion in the semantic space by applying iterations with some homography parameters allowed to vary and others blocked from varying and subsequent iterations with all homography parameters allowed to vary.

The present invention provides an image processing apparatus that inspects an image formed on a printing medium. The image processing apparatus reads an image formed on a printing medium and obtains a target image to be inspected, and corrects a position of control point among control points disposed on the target image, at or near an edge of the printing medium, and performs alignment using the corrected position of the control point so as to align the target image to a reference image using a non-rigid-body alignment, and inspects for a defect in the target image on a basis of the aligned target image and the reference image. In the correcting, a position of a control point at or near the edge is corrected on a basis of an interval between adjacent control points at or near the edge.

A computing system includes one or more processors and a memory storing instructions that, when executed by the one or more processors, cause the system to perform operations. The operations include determining that a portion of an existing map is to be updated; obtaining a point cloud acquired by one or more Lidar sensors corresponding to a location of the portion; converting the portion into an equivalent point cloud; performing a point cloud registration based on the equivalent point cloud and the point cloud; and updating the existing map based on the point cloud registration.

A system, article, and method of point cloud registration using overlap regions for image processing.

A method may be provided to operate a medical system. First data may be provided for a first 3-dimensional (3D) image scan of an anatomical volume, with the first data identifying a blood vessel node in a first coordinate system for the first 3D image scan. Second data may be provided for a second 3D image scan of the anatomical volume, with the second data identifying the blood vessel node in a second coordinate system for the second 3D image scan. The first and second coordinate systems for the first and second 3D image scans of the anatomical volume may be co-registered using the blood vessel node identified in the first data and in the second data as a fiducial.