Abstract: The graphics processing unit (GPU) of a processing system transitions to a low-power state between frame rendering operations according to an inter-frame power off process, where GPU state information is stored on retention hardware. The retention hardware can include retention random access memory (RAM) or retention flip-flops. The retention hardware is operable in an active mode and a retention mode, where read/write operations are enabled at the retention hardware in the active mode and disabled in the retention mode, but data stored on the retention hardware is still retained in the retention mode. The retention hardware is placed in the retention state between frame rendering operations. The GPU transitions from its low-power state to its active state upon receiving an indication that a new frame is ready to be rendered and is restored using the GPU state information stored at the retention hardware.

Abstract: Data structures, methods and tiling engines for storing tiling data in memory wherein the tiles are grouped into tile groups and the primitives are grouped into primitive blocks. The methods include, for each tile group: determining, for each tile in the tile group, which primitives of each primitive block intersect that tile; storing in memory a variable length control data block for each primitive block that comprises at least one primitive that intersects at least one tile of the tile group; and storing in memory a control stream comprising a fixed sized primitive block entry for each primitive block that comprises at least one primitive that intersects at least one tile of the tile group, each primitive block entry identifying a location in memory of the control data block for the corresponding primitive block. Each primitive block entry may comprise valid tile information identifying which tiles of the tile group are valid for the corresponding primitive block.

Abstract: Various methods are provided for the generation of motion vectors in the context of 3D computer-generated images. In one example, a method includes generating, for each pixel of one or more objects to be rendered in a current frame, a 1-phase motion vector (MV1) and a 0-phase motion vector (MV0), each MV1 and MV0 having an associated depth value, to thereby form an MV1 texture and an MV0 texture, each MV0 determined based on a camera MV0 and an object MV0, converting the MV1 texture to a set of MV1 pixel blocks and converting the MV0 texture to a set of MV0 pixel blocks and outputting the set of MV1 pixel blocks and the set of MV0 pixel blocks for image processing.

Abstract: Techniques for determination of an optimal spatiotemporal sensor configuration for navigation of a vehicle include generating a model of a virtual vehicle operating in an environment. The model of the virtual vehicle includes a virtual sensor having a virtual viewing range. The virtual viewing range of the virtual sensor is segregated into frustums. The virtual viewing range of the virtual sensor corresponds to a viewing range of a sensor of a vehicle operating in the environment. A geometric viewport is generated including pixels. The geometric viewport has a height corresponding to a number of rays emitted from the virtual sensor. The geometric viewport is segregated into sections. Each section corresponds to a frustum. A virtual point cloud of the virtual sensor is rendered. The virtual point cloud includes coordinate positions representing a portion of the environment located within the virtual viewing range of the virtual sensor.

Abstract: Systems and techniques are provided for determining bounding regions for a hierarchical structure for ray tracing. For instance, a process can include obtaining an acceleration data structure, the acceleration data structure including one or more primitives of a scene object. A graph cut can be applied to the acceleration data structure. A set of nodes of the acceleration data structure can be determined based on the graph cut, wherein the determined set of nodes is located adjacent to the graph cut. A world-space bounding box can be generated for the scene object, using the set of nodes determined based on the graph cut.

Abstract: Rendering system combines point sampling and volume sampling operations to produce rendering outputs. For example, to determine color information for a surface location in a 3-D scene, one or more point sampling operations are conducted in a volume around the surface location, and one or more sampling operations of volumetric light transport data are performed farther from the surface location. A transition zone between point sampling and volume sampling can be provided, in which both point and volume sampling operations are conducted. Data obtained from point and volume sampling operations can be blended in determining color information for the surface location. For example, point samples are obtained by tracing a ray for each point sample, to identify an intersection between another surface and the ray, to be shaded, and volume samples are obtained from a nested 3-D grids of volume elements expressing light transport data at different levels of granularity.

Abstract: Aspects relate to tracing rays in 3-D scenes that comprise objects that are defined by or with implicit geometry. In an example, a trapping element defines a portion of 3-D space in which implicit geometry exist. When a ray is found to intersect a trapping element, a trapping element procedure is executed. The trapping element procedure may comprise marching a ray through a 3-D volume and evaluating a function that defines the implicit geometry for each current 3-D position of the ray. An intersection detected with the implicit geometry may be found concurrently with intersections for the same ray with explicitly-defined geometry, and data describing these intersections may be stored with the ray and resolved.

Abstract: One or more computing devices implement a mesh analysis for evaluating meshes to be rendered when rendering immersive content. The mesh analysis identifies objects in a three-dimensional scene and determines geometrical complexity values for the objects. Objects with similar geometrical complexities are grouped into areas and a mesh vertices budget is determined for the respective areas. Metadata indicating the area definitions and corresponding mesh vertices budgets are generated. The metadata may be uploaded to a server to simplify meshes in the scene prior to streaming to a client, or the metadata may be provided to a client for use in simplifying the meshes as part of rendering the scene.

Abstract: Procedural world generation using tertiary data is described. In an example, a computing device can receive road network data associated with the real environment and a road mesh associated with a real environment. The computing device can associate the road network data with the road mesh to generate a simulated environment. Additionally, the computing device can associate supplemental data with the road network data and the road mesh to enhance the simulated environment (e.g., supplementing information otherwise unavailable to the sensor data due to an occlusion). The computing device can output the simulated environment for at least one of testing, validating, or training an algorithm used by an autonomous robotic computing device for at least one of navigating, planning, or decision making.

Abstract: A tetrahedral interpolation calculation method and apparatus, a gamut conversion method and apparatus, and a medium are provided, the tetrahedral interpolation calculation method comprising: obtaining coordinates of an interpolation point in a sampling space, a side length of a cube formed of nearby eight sampling points surrounding the interpolation point in the sampling space, and mapping values of four vertices of a tetrahedron surrounding the interpolation point, wherein the four vertices are four out of the eight sampling points; calculating a volume of the tetrahedron, and volumes of four sub-tetrahedrons formed of the interpolation point and arbitrary three vertices in the tetrahedron, based on coordinates of the interpolation point in the sampling space, and the side length of the cube formed of nearby eight sampling points surrounding the interpolation point in the sampling space; and obtaining an interpolation value of the interpolation point, based on a tetrahedral interpolation theorem formula, th

Abstract: A method and apparatus are provided for tessellating patches of surfaces in a tile based three dimensional computer graphics rendering system. For each tile in an image a per tile list of primitive indices is derived for tessellated primitives which make up a patch. Hidden surface removal is then performed on the patch and any domain points which remain after hidden surface removal are derived. The primitives are then shaded for display.

Abstract: A method for merging surface skin three-dimensional (3D) data includes the following steps: 1. constructing actually-measured 3D data of a workpiece and 3D data of a design model of the workpiece; 2. calculating a normal vector, a neighborhood radius, and a position of a sphere center of each point in the design model 3D data; 3. finding closest points to the design model 3D data for all points in the actually-measured 3D data; 4. calculating a static closest distance and a dynamic closest distance from each point in the actually-measured 3D data to the closest point in the design model 3D data; 5. constructing an objective function of a surface adaptive distance; 6. minimizing the objective function and calculating a differential motion screw; and 7. updating the actually-measured 3D data and achieving data merging.

Abstract: A system, software application and process help the user memorize a digital environment through the process of actions the users have to perform. The embodiments provide generating a digital environment including a first virtual room. A first set of digital objects in pre-defined locations of the first virtual room is generated. The first virtual room and the digital objects in the pre-defined locations are displayed. An acknowledgement from the user that the user has memorized positions of each of the digital objects in the first virtual room is received. The objects are removed. Selection of the digital objects and their placement in the first virtual room is received. The system determines whether every digital object was placed in a correct location and in response, generates a second virtual room including a second set of digital objects for further memory training.

Abstract: Systems, methods, devices, and media for anamorphosis systems to generate and cause display of anamorphic media are disclosed. In one embodiment, an anamorphosis system is configured to identify a set of features of a space, determine relative positions of the set of features, determine a perspective of the mobile device within the space based on the relative positions of the set of features, retrieve anamorphic media based on the location of the mobile device, and apply the anamorphic media to a presentation of the space at the mobile device. The anamorphic media may include media items such as images and videos, configured such that the media items are only visible from one or more specified perspectives. The anamorphic media may include a stylized text string projected onto surfaces of a space such that the stylized text string is correctly displayed when viewed through a user device from a specified perspective.

Abstract: A method for placing content in an augmented reality system. A notification is received regarding availability of new content to display in the augmented reality system. A confirmation is received that indicates acceptance of the new content. Three dimensional information that describes the physical environment is provided, to an external computing device, to enable the external computing device to be used for selecting an assigned location in the physical environment for the new content. Location information is received, from the external computing device, that indicates the assigned location. A display location on a display system of the augmented reality system at which to display the new content so that the new content appears to the user to be displayed as an overlay at the assigned location in the physical environment is determined, based on the location information. The new content is displayed on the display system at the display location.

Abstract: A method performed by a first terminal is provided. The method includes identifying capabilities of the first terminal connected to at least one component device, establishing, via a server, a session associated with an augmented reality (AR) service based on the capabilities of the first terminal, performing pre-processing on 3 dimensional (3D) media data acquired by the at least one component device, and transmitting, to a second terminal, the pre-processed 3D media data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating composite images. One of the methods includes maintaining first data associating each location within an environment with a particular time; obtaining an image depicting the environment from a point of view of a display device; obtaining second data characterizing one or more virtual objects; and processing the obtained image and the second data to generate a composite image depicting the one or more virtual objects at respective locations in the environment from the point of view of the display device, wherein the composite image depicts each virtual object according to the particular time that the first data associates with the location of the virtual object in the environment.

Abstract: An apparatus comprising means for: means for joining to at least an existing participant in extended reality at a location in a virtual space, a joining participant in extended reality to enable a shared extended reality, wherein the joined participants in the shared extended reality are at least co-located in the virtual space and can share at least visually the virtual space; wherein at least part of a content configuration is inherited from the existing participant by the joining participant, wherein the content configuration controls, for participants, what is heard, what is seen and interactivity with the virtual space; wherein at least part of a join configuration is inherited between the existing participant and the joining participant, wherein the join configuration controls joining of other joining participants in the shared extended reality.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for presenting available augmented reality (AR) content items. The program and method provide for displaying a capture interface in accordance with a camera mode configured to capture multiple video clips; displaying a carousel interface for presenting a first set of AR content items, each being selectable to apply respective AR content to captured video; receiving first user input selecting an explore tab included which is selectable to switch to an explorer interface for presenting a second set of AR content items; switching from the capture interface to the explorer interface; receiving, via the explorer interface, second user input selecting an AR content item from among the second set; and updating, in response to receiving the second user input, the first set of AR content items to include the selected AR content item.

Abstract: Systems, methods, and computer readable media for enhanced augmented reality (AR) reading are provided, where the methods include entering a reading mode, capturing an image of a section of reading materials such as a page of a book, identifying a code within the image, and identifying a code module corresponding to the code. The methods further include executing the code module, the code module providing an augmented reality object or virtual reality object related to an object depicted on the section or page, entering a sleep mode for a sleep duration based on an estimated reading time duration of a section or page, awaking after the sleep duration, and capturing a next image. The sleep duration is adjusted based on times when identifiers of the sections of the reading materials such as numbers are captured. The user may manually wake the AR reading device using an external user interface.

Abstract: An augmented reality system is provided, including a physical apparatus operable to change detectably by a human between a first state and a second state, and an augmented reality application. The physical apparatus includes a signal receiver for receiving a signal, and at least one controllable element operable to effect the change between the first state and the second state upon receiving the signal. The AR application, when executed by at least one processor of a computing device, the computing device having at least one camera and a display, cause the computing device to capture at least one image of the physical apparatus, generate a virtual reality object that is presented in the at least one image on the display, and transmit the signal to the physical apparatus to cause the at least one controllable element of the physical apparatus to switch between the first state and the second state.

Abstract: Disclosed are systems and methods for mixed reality collaboration. A method may include receiving persistent coordinate data; presenting a first virtual session handle to a first user at a first position via a transmissive display of a wearable device, wherein the first position is based on the persistent coordinate data; presenting a virtual object to the first user at a second location via the transmissive display, wherein the second position is based on the first position; receiving location data from a second user, wherein the location data relates a position of the second user to a position of a second virtual session handle; presenting a virtual avatar to the first user at a third position via the transmissive display, wherein the virtual avatar corresponds to the second user, wherein the third position is based on the location data, and wherein the third position is further based on the first position.

Abstract: Methods and systems for selectively smoothing an input surface mesh based on identified staircase artifacts are disclosed. Staircase artifacts may be generated along any one of a surface mesh's coordinate vectors. Vertices in the surface mesh associated with the staircase artifact are identified by comparing normalized angles between normal vectors of a plurality of faces adjacent to a vertex and a reference vector. Multiple reference vectors are used to identify additional artifact vertices. Weighted values may be generated for each vertex of the surface mesh based on the vertex's proximity to an identified artifact vertex. Vertices of a surface mesh may be subjected to a modified smoothing algorithm using the weighted values. The modified smoothing algorithm removes staircase artifacts while better preserving model volume and small model features.

Abstract: An electronic device and method for positioning an eyeball into a 3D mesh of a head portion of an object is provided. Images of an eye of an object, the 3D mesh of the head portion of the object, and a 3D template mesh of an eyeball are acquired. 3D feature points for eye regions are extracted from the images and fit to a sphere. An initial pose transformation between the 3D template mesh and the sphere is estimated. Based on the 3D template mesh, a first set of points corresponding to the eye regions are interpolated. Based on sampling parameters for the first set of points, a second set of points are determined. A final pose transformation is determined based on minimization of difference between the first and the second set of points and the 3D template mesh is fit into an eyeball socket of the 3D mesh.

Abstract: A system and method of calibrating a broadcast video feed are disclosed herein. A computing system retrieves a plurality of broadcast video feeds that include a plurality of video frames. The computing system generates a trained neural network, by generating a plurality of training data sets based on the broadcast video feed and learning, by the neural network, to generate a homography matrix for each frame of the plurality of frames. The computing system receives a target broadcast video feed for a target sporting event. The computing system partitions the target broadcast video feed into a plurality of target frames. The computing system generates for each target frame in the plurality of target frames, via the neural network, a target homography matrix. The computing system calibrates the target broadcast video feed by warping each target frame by a respective target homography matrix.

Abstract: In a method of color decomposition, inter-color images indicating similarity between color sensitivities are generated based on color images. Conversion coefficients of the color images and the inter-color images with respect to a white image are determined. A pseudo-white image corresponding to the color images and the inter-color images is generated using the conversion coefficients the pseudo-white image similar to a real white image is generated using the inter-color images indicating similarity between color sensitivities. Deep learning of the artificial neural network is performed efficiently using the color images and the pseudo-white image and the demosaiced images of high quality are generated using the trained artificial neural network that is trained.

Abstract: An electronic device is disclosed. The electronic device of the disclosure comprises: a memory in which a learned artificial intelligence model is stored; and a processor for inputting an input image to the artificial intelligence model and outputting an enlarged image with increased resolution, wherein the learned artificial intelligence model includes an upscaling module for acquiring the pixel values of interpolated pixels around a cell according to a function having a nonlinearly decreasing symmetric form with reference to an original pixel in the enlarged image, the original pixel corresponding to a pixel of the input image.

Abstract: An electronic apparatus is disclosed. The electronic apparatus includes a memory storing at least one instruction, and a processor, electrically connected to the memory, configured to, by executing the instruction, obtain, from an input image, a noise map corresponding to the input image; provide the input image to an input layer of a learning network model including a plurality of layers, the learning network model being an artificial intelligence (AI) model that is obtained by learning, through an AI algorithm, a relationship between a plurality of sample images, a respective noise map of each of the plurality of sample images, and an original image corresponding to the plurality of sample images; provide the noise map to at least one intermediate layer among the plurality of layers; and obtain an output image based on a result from providing the input image and the noise map to the learning network model.

Abstract: This application provides an image dehazing method, apparatus, and device, and a computer storage medium. The method includes: in response to obtaining an image dehazing instruction, acquiring a first image and a second image corresponding to a target scene at the same moment. The method also includes calculating, based on a first pixel value of each pixel of the first image and a second pixel value of each pixel of the second image, haze density information of the each pixel; generating an image fusion factor of the each pixel according to the haze density information, the image fusion factor indicating a fusion degree between the first image and the second image; and fusing the first image and the second image according to the image fusion factor to obtain a dehazed image.

Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.

Abstract: A camera parameter estimation apparatus 10 for estimating geometric parameters of a camera that has shot an image of an object and a lens distortion parameter of a lens distortion model represented by a single unknown. The camera parameter estimation apparatus 10 includes: a data obtaining unit 11 that obtains image corresponding points relating to the object and an approximation order for polynomial approximation of the lens distortion model; and a parameter estimation unit 12 that estimates, based on the image corresponding points and the approximation order, the geometric parameter and the lens distortion parameter that minimize an error function representing a specific transformation of the image corresponding points.

Abstract: A method for correcting a distorted image includes: acquiring a first coordinate of each pixel in a distorted image to be corrected; determining internal parameters for shooting the distorted image; acquiring a second coordinate corresponding to the first coordinate based on a corresponding relationship between the internal parameters and image distortion degrees, in which the second coordinate is an undistorted coordinate; acquiring a distance between the first coordinate and a coordinate of a center point of the distorted image, and determining a smoothing processing coefficient corresponding to the distance based on a smoothing processing function, in which the smoothing processing function is configured to indicate a proportional relationship between the distance and the smoothing processing coefficient; and acquiring a distortion correction image by performing smoothing correction on each first coordinate based on the smoothing processing coefficient and the second coordinate.

Abstract: Disclosed herein are an apparatus and method for sensing an image based on an event. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may perform acquiring at least one of brightness information and color information from an input image signal, performing conversion including at least one of filtering of at least one of the acquired brightness information and color information, color conversion, and brightness conversion, calculating a quantized difference between a first converted image converted from the currently input image signal and a second converted image converted from a previously input image signal, and generating event information for the input image signal as a bitstream based on the quantized difference.

Abstract: Provided are a method and apparatus for creating a composite image, by which the state of a target may be effectively expressed, and a computer program stored in a recording medium to execute the method. The composite image creating method, performed by a computing apparatus, of synthesizing an input image to a target image, includes identifying information of the input image by obtaining the input image, generating a projected image based on information about a position in units of sub-pixels for the target image of the input image, by using information of the input image, generating a reduced image by reducing the projected image at a ratio corresponding to the target image, and synthesizing the reduced image to the target image.

Abstract: A system and a method for detecting image forgery through a convolutional neural network are capable of detecting image manipulation of compressed and/or color images. The system comprises a manipulated feature pre-processing unit applying an input image to a high-pass filter to enhance features due to image forgery; a manipulated feature extraction unit extracting image manipulated feature information from the image with the enhanced features through a pre-trained convolutional neural network; a feature refining unit refining the extracted image manipulated feature information; and a manipulation classifying unit determining the image forgery based on the image manipulated feature information refined by the feature refining unit.

Abstract: The invention relates to a method implemented by a data processing apparatus, comprising the steps of receiving an image; providing a set-point for a desired image quality parameter of said image; and processing said image using an image analysis technique for determining a current image quality parameter of said image. In the method, the current image quality parameter is compared with said desired set-point. Based on said comparison, a modified image is generated by using an image modification technique. The generating comprises the steps of improving said image in terms of said image quality parameter in case said current image quality parameter is lower than said set-point; and deteriorating said image in terms of said image quality parameter in case said current image quality parameter exceeds said set-point. The modified image is then output.

Abstract: A defect inspection system is disclosed. According to certain embodiments, the system includes a memory storing instructions implemented as a plurality of modules. Each of the plurality of modules is configured to detect defects having a different property. The system also includes a controller configured to cause the computer system to: receive inspection data representing an image of a wafer; input the inspection data to a first module of the plurality of modules, the first module outputs a first set of points of interests (POIs) having a first property; input the first set of POIs to a second module of the plurality of modules, the second module output a second set of POIs having the second property; and report that the second set of POIs as defects having both the first property and the second property.

Abstract: A system and method for calibrating a machine vision system on the undercarriage of a rail vehicle while the rail vehicle is in the field is presented. The system enables operators to calibrate the machine vision system without having to remove the machine vision system from the undercarriage of the rail vehicle. The system can capture, by a camera of an image capturing module, a first image of a target. The image capturing module and a drum can be attached to a fixture and the target can be attached to the drum. The system can also determine a number of lateral pixels in a lateral pitch distance of the image of the target, determining a lateral object pixel size based on the number of lateral pixels, and determining a drum encoder rate based on the lateral object pixel size. The drum encoder rate can be programmed into a drum encoder.

Abstract: Systems and methods are provided to perform PdM surveys using data acquisition units which scan screen multiple locations where equipment or structures to be evaluated are present. Video data will be acquired and processed to measure translational and vibratory motion and additional data will be collected from other camera, sensors or via data links. The motion present in the equipment or structures under test and the supplemental data will be automatically evaluated to detect suspect equipment conditions and to minimize the amount of video data maintained on the data acquisition unit and transmitted back the central PdM server for review by a PdM analyst and long term archival.

Abstract: Stock management for wood and lumber products requires measuring and counting items individually on a continuous basis; considering a single lumber package alone can contain hundreds of pieces, it is a tedious task that is error prone when done manually. The invention provides a technology solution that involves taking a picture of products using a smart-phone, or a tablet's built-in camera, processing said picture data to detect individual items using Artificial Intelligence Object Detection methods, and utilizing special algorithms to measure and compute unit volume to present the user a detailed description, measure, count, and a summary. This process helps identify and take stock counts faster and with higher accuracy.

Abstract: An image recognition device and method retrieve information on a marker. The marker encodes information identifying an asset by encoding the information in a binary pattern as recesses and non-recesses in the marker. The image recognition is performed by imaging the marker, mapping contrast in the image, identifying variations in the contrast, creating a mesh overlaying the image, identifying the present or absence of recesses from the mesh, and reading the binary pattern represented by the recesses in the marker.

Abstract: Disclosed herein are methods for quantifying contact lens deposition. An example method may comprise disposing a contact lens sample in a fluid well. The example method may comprise disposing a volume of tear fluid in the well with the contact lens sample. The example method may comprise capturing pre-rinse images of the contact lens sample. The example method may comprise rinsing the contact lens sample. The example method may comprise capturing post-rinse images of the contact lens after the rinsing. The example method may comprise determining, using one or more of the tear images or the post-rinse images, a deposition metric. The example method may comprise outputting the deposition metric.

Abstract: An overlay metrology system may include a controller for receiving metrology data associated with a plurality of overlay targets on one or more samples; generating a reference metric for at least some of the plurality of overlay targets based on the metrology data, where the reference metric is associated with one or more properties of the respective overlay targets that contributes to overlay error; classifying the plurality of overlay targets into one or more groups based on the reference metrics calculated for the plurality of overlay targets; generating a reference image for at least some of the one or more groups; generating corrected metrology data using the associated reference image for at least some of the one or more groups; and generating overlay measurements for the plurality of overlay targets based on the corrected metrology data.

Abstract: A method for classifying a vasculature comprises training a training device with an initial model of a vasculature using diagnostic image data representing a geometry for a plurality of vessels of a vessel tree and including a respective vessel labeling for each vessel, providing at least one diagnostic image of a patient's vessel tree and identifying a variation between the vessel tree represented by the initial model and the patients vessel tree. This variation is checked and labeled in order to improve the trained model. The process may be repeated iteratively until reaching an accurate patient-specific model of the vasculature.

Abstract: At the time of superimposing and aligning a stained image and a mass spectrometric (MS) image obtained for the same sample, an image display processor displays, on the superimposed images, grid lines (62) at the spacing corresponding to an operation of a grid spacing adjustment slider (63). When an operator depresses an image deformation range “SET” button (64), specifies an arbitrary area on the superimposed images with a mouse, and then depresses a “SELECT” button (65), an image deformation range specification receiving section determines an image deformation range. When the operator selects an intersection (grid point) of the grid lines (62) within the image deformation range and performs an operation of moving the intersection point to an arbitrary position, an image deformation processor deforms an image included in the image deformation range in accordance with the operation.

Abstract: The disclosure relates to techniques for automatically characterizing liver tissue of a patient, comprising receiving morphological magnetic resonance image data set and at least one magnetic resonance parameter map of an imaging region comprising at least partially the liver of the patient, each acquired by a magnetic resonance imaging device, via a first interface. The techniques further include applying a trained function comprising a neural network to input data comprising at least the image data set and the parameter map. At least one tissue score describing the liver tissue is generated as output data, which is provided using a second interface.

Abstract: Systems and methods for quantifying a shift of an anatomical object of a patient are provided. A 3D medical image of an anatomical object of a patient is received. An initial location of landmarks on the anatomical object in the 3D medical image is determined using a first machine learning network. A 2D slice depicting the initial location of the landmarks is extracted from the 3D medical image. The initial location of the landmarks in the 2D slice is refined using a second machine learning network. A shift of the anatomical object is quantified based on the refined location of the landmarks in the 2D slice. The quantified shift of the anatomical object is output.

Abstract: The present disclosure provides a deep learning based medical image detection method and apparatus, a computer-readable medium, and an electronic device. The method includes: acquiring a to-be-detected medical image comprising a plurality of slices; for each slice in the to-be-detected medical image: extracting N basic feature maps of the slice by a deep neural network, N being an integer greater than 1, merging features of the N basic feature maps by the deep neural network, to obtain M enhanced feature maps, M being an integer greater than 1, and respectively performing a hierarchically dilated convolutions operation on the M enhanced feature maps by the deep neural network, to generate a superposed feature map of each enhanced feature map; and predicting position information of a region of interest and a confidence score thereof in the to-be-detected medical image by the deep neural network based on the superposed feature map.

Abstract: Provided herein is technology relating to analysis of images and particularly, but not exclusively, to methods and systems for determining the area and/or volume of a region of interest using optical coherence tomography data. Some embodiments provide for determining the area and/or volume of a lesion in retinal tissue using three-dimensional optical coherence tomography data and a two-dimensional optical coherence tomography fundus image.

Abstract: Systems and methods are disclosed for predicting the location, onset, or change of coronary lesions from factors like vessel geometry, physiology, and hemodynamics. One method includes: acquiring, for each of a plurality of individuals, a geometric model, blood flow characteristics, and plaque information for part of the individual's vascular system; training a machine learning algorithm based on the geometric models and blood flow characteristics for each of the plurality of individuals, and features predictive of the presence of plaque within the geometric models and blood flow characteristics of the plurality of individuals; acquiring, for a patient, a geometric model and blood flow characteristics for part of the patient's vascular system; and executing the machine learning algorithm on the patient's geometric model and blood flow characteristics to determine, based on the predictive features, plaque information of the patient for at least one point in the patient's geometric model.