Abstract: A coating analyzer is configured to receive electronic image data of a physical coating and to generate information regarding the pigments of the physical coating. The coating analyzer applies a computer vision model trained on baseline image data to the electronic image data. The coating analyzer assigns color values to the pigments forming the electronic image data and generates pigment groups based on the assigned color values. The pigment groups provide color palette data regarding the pigments forming the coating.

Abstract: A method of estimating the movement between two images (I1, I2) comprising the steps of determining an initialization displacement vector between the two images by projecting, in the image plane of the image capture device, the displacement between the two images calculated depending on collected information defining the movement of the image capture device between the two images and depending on the value of image capture parameter(s) used, chosen from an angular opening, a zoom factor and the resolution of the images implementing, based on the initialization displacement vector, an iterative algorithm delivering a displacement vector depending on an error function to be minimized between one of the two images and the transform of the other image by the displacement vector.

Abstract: The technology relates to determining whether a camera is occluded. For instance, an image may be captured using a camera having red, green, and blue pixels each including a photosensor. Output values for the photosensors of each of the red pixels, green pixels, and blue pixels may be determined for the images. The output values of the green pixels may be compared to one or more of the output values of the red pixels or the output values of the blue pixels. That the camera is occluded is determined based on the comparison.

Abstract: A method for enabling a user to paint an image uploaded to a device is provided. The method includes uploading an image to the device, performing a depth estimation on the image to generate a depth map, and performing an edge detection on the image to generate a first edge map. The method also includes performing the edge detection on the depth map to generate a second edge map, performing a skeletonization function on the first edge map to generate a third edge map, and performing the skeletonization function on the depth map to generate a fourth edge map. The method also includes generating a final edge map using the third edge map and the fourth edge map, generating a colorized image by applying color to the final edge map to paint at least one wall of a scene, and displaying the colorized image on a display of the device.

Abstract: For reconstruction in medical imaging, such as reconstruction in MR imaging, an iterative, hierarchal network for regularization may decrease computational complexity. The machine-learned network of the regularizer is unrolled or made iterative. For each iteration, nested U-blocks form a hierarchy so that some of the down-sampling and up-sampling of some U-blocks begin and end with lower resolution data or features, reducing computational complexity.

Abstract: Images may be altered based on ON-OFF visual pathway information processing. A process for generating altered images may include separating an original image into distinct images based on luminance values for each pixel of the pixels that form the original image. The distinct images may include a first and a second separated image, where each separated image includes distinct pixels. Additionally, the process may include determining a first luminance range for the first separated image based on the luminance value for each pixel forming the first separated image, and determining a second luminance range for the second separated image based on the luminance value for each pixel forming the second separated image. The process may also include adjusting visual parameters of the first and second separated images, and combining the adjusted, first and second separated images to generate the altered image.

Abstract: Techniques for machine learning based image attribute determination are disclosed. In some embodiments, one or more unknown attributes of a received image comprising a prescribed environment are determined using a machine learning based framework. The machine learning based framework is at least in part trained on image data sets comprising a model environment that substantially simulates the prescribed environment.

Abstract: The method for item identification preferably includes determining visual information for an item; calculating a first encoding using the visual information; calculating a second encoding using the first encoding; determining an item identifier for the item using the second encoding; optionally presenting information associated with the item to a user; and optionally registering a new item.

Abstract: An image retrieval system receives an image for which to identify relevant images from an image repository. Relevant images may be of the same environment or object and features and other characteristics. Images in the repository are represented in an image retrieval graph by a set of image nodes connected by edges to other related image nodes with edge weights representing the similarity of the nodes to each other. Based on the received image, the image traversal system identifies an image in the image retrieval graph and alternatively explores and traverses (also termed “exploits”) the image nodes with the edge weights. In the exploration step, image nodes in an exploration set are evaluated to identify connected nodes that are added to a traversal set of image nodes. In the traversal step, the relevant nodes in the traversal set are added to the exploration set and a query result set.

Abstract: Techniques for generating an image are disclosed. In some embodiments, a received input image is transformed to generate an output image using a machine learning based framework that is trained on a constrained set of images. The generated output image comprises an attribute learned by the machine learning based framework from the set of images.

Abstract: A machine learning based image processing and generation framework is disclosed. In some embodiments, depth values of an object or asset in a received input image are at least in part determined using a machine learning based framework that is constrained to a known prescribed environment. Determined depth values facilitate generation of other views of the object or asset.

Abstract: Disclosed herein are methods, systems, and computer-readable media for regenerating a region of an image with a machine learning model based on a text input. Disclosed embodiments involve accessing a digital input image. Disclosed embodiments involve generating a masked image by removing a masked region from the input image. Disclosed embodiments involve accessing a text input corresponding to an image enhancement prompt. Disclosed embodiments include providing at least one of the input image, the masked region, or the text input to a machine learning model configured to generate an enhanced image. Disclosed embodiments involve generating, with the machine learning model, the enhanced image based on at least one of the input image, the masked region, or the text input.

Abstract: Techniques for generating an arbitrary view or perspective of an ensemble scene are disclosed. In some embodiments, in response to a received request for a prescribed perspective of an ensemble scene comprising a plurality of assets, an output image of the ensemble scene for the requested prescribed perspective is generated based at least in part on combining at least a portion of an existing image of each of at least a subset of the plurality of assets.

Abstract: A semiconductor image classifier. Convolution functions are applied to modify the wafer images in order to extract key information about the image. The modified images are condensed then processed through a series of pairwise classifiers, each classifier configured to determine that the image is more like one of the pair than the other. Probabilities from each classifier are collected to form a prediction for each image.

Abstract: Aspects of the disclosure provide methods and apparatuses for point cloud compression and decompression. In some examples, an apparatus for point cloud compression/decompression includes processing circuitry. In some examples, the processing circuitry receives a bitstream carrying compressed data for a point cloud. The processing circuitry determines that a current node in an octree structure is eligible for an isolated mode. The octree structure corresponds to three dimensional (3D) partitions of a space of the point cloud. Then the processing circuitry determines, based on information of one or more other nodes, a single isolated point flag for the current node that indicates whether the current node is coded with a single isolated point.

Abstract: Embodiments of this application provide a measurement method and a measurement apparatus. The measurement method includes: acquiring a first image and a second image of a target object, where the first image is acquired by a camera located on a non-backlight side of the target object, and the second image is acquired by a camera located on a backlight side of target object; and measuring the target object for size information according to the first image and the second image. The technical solution of this application can improve accuracy and precision of inspection while improving production efficiency.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a classification neural network.

Abstract: An image compression sampling method and assembly are provided. The method includes: performing sparse representation on a target image by using an initial sparse matrix, quantifying an initial sparse representation result to obtain an optimized sparse representation result, and obtaining an optimized sparse matrix; constructing a product matrix by using the optimized sparse matrix and an initial measurement matrix, and adjusting absolute values of off-diagonal elements in the product matrix to be less than a correlation threshold; performing singular value decomposition on the product matrix to obtain a diagonal matrix and a left singular matrix, and updating the diagonal matrix according to a quantity of samplings of the initial measurement matrix; and optimizing the initial measurement matrix by using the left singular matrix and the updated diagonal matrix to obtain an optimized measurement matrix, and collecting image data by using the optimized sparse matrix and the optimized measurement matrix.

Abstract: A construction method and system for a visible near-infrared spectrum dictionary is provided. The method includes: constructing a four-primary color chromaticity cone by using normalized spectral response curves of four primary colors of a visible light camera as spectral basis functions; performing weighted combination on the spectral basis functions and forming an initial visible near-infrared spectrum dictionary; acquiring points on the four-primary color chromaticity cone on the basis of the initial visible red infrared spectrum dictionary according to different spectral resolutions and performing discretization, and forming words in the initial visible near-infrared spectrum dictionary; clustering chromaticity coordinates corresponding to the words into different groups, performing weighted combination on multi-scale spectral response curves corresponding to different group types, generating phrases or sentences in the dictionary, and generating a final visible near-infrared spectrum dictionary.

Abstract: Provided is an image processing method, which includes: determining whether the number of written rows of source image data in a DDR is a preset number of rows or a stop write number of rows, the preset number of rows being an integer multiple of the number of rows of an image block determined according to a compression condition, and the image block being any image block in an image block matrix determined on the basis of an entire frame of image; if yes, reading the source image data of the current image block from the DDR on the basis of a first read address of the current image block, the number of rows, and the number of columns; and performing compression on the source image data of the current image block to obtain compressed data, and writing the compressed data to the DDR.