Abstract: Ray tracing systems have computation units (“RACs”) adapted to perform ray tracing operations (e.g. intersection testing). There are multiple RACs. A centralized packet unit controls the allocation and testing of rays by the RACs. This allows RACs to be implemented without Content Addressable Memories (CAMs) which are expensive to implement, but the functionality of CAMs can still be achieved by implemented them in the centralized controller.

Abstract: Ray tracing systems and computer-implemented methods are described for performing intersection testing on a bundle of rays with respect to a box. Silhouette edges of the box are identified from the perspective of the bundle of rays. For each of the identified silhouette edges, components of a vector providing a bound to the bundle of rays are obtained and it is determined whether the vector passes inside or outside of the silhouette edge. Results of determining, for each of the identified silhouette edges, whether the vector passes inside or outside of the silhouette edge, are used to determine an intersection testing result for the bundle of rays with respect to the box.

Abstract: A method and an intersection testing module for performing intersection testing of a ray with a box in a ray tracing system. The ray and the box are defined in a 3D space using a space-coordinate system, and the ray is defined with a ray origin and a ray direction. A ray-coordinate system is used to perform intersection testing, wherein the ray-coordinate system has an origin at the ray origin, and the ray-coordinate system has three basis vectors. A first of the basis vectors is aligned with the ray direction. A second and a third of the basis vectors: (i) are both orthogonal to the first basis vector, (ii) are not parallel with each other, and (iii) have a zero as one component when expressed in the space-coordinate system. A result of performing the intersection testing is outputted for use by the ray tracing system.

Abstract: A sensor simulation system may generate sensor data for use in simulations by rendering two-dimensional views of a three-dimensional simulated environment. In various examples, the sensor simulation system uses sensor dependency data to determine specific views to be re-rendered at different times during the simulation. The sensor simulation system also may generate unified views with multi-sensor data at each region (e.g., pixel) of the two-dimensional view for consumption by different sensor types. A hybrid technique may be used in some implementations in which rasterization is used to generate a view, after which ray tracing is used to align the view with a particular sensor. Spatial and temporal upsampling techniques also may be used, including depth-aware and velocity-aware analyses for simulated objects, to improve view resolution and reduce the frequency of re-rendering views.

Abstract: The present invention provides a method for reconstructing a 3D object based on dynamic graph network, first, obtaining a plurality of feature vectors from 2D image I of an object; then, preparing input data: predefining an initial ellipsoid mesh, obtaining a feature input X by filling initial features and creating a relationship matrix A corresponding to the feature input X; then, inputting the feature input X and corresponding relationship matrix A to a dynamic graph network for integrating and deducing of each vertex's feature, thus new relationship matrix is obtained and used for the later graph convoluting, which improves the initial graph information and makes the initial graph information adapted to the mesh relation of the corresponding object, therefore the accuracy and the effect of 3D object reconstruction have been improved; last, regressing the position, thus the 3D structure of the object is deduced, and the 3D object reconstruction is completed.

Abstract: Embodiments of a method and apparatus for generating a virtual avatar, a device and a storage medium are provided. The method may include: determining a template coefficient of a target face in a to-be-processed image based on at least two real face feature templates; and determining a virtual avatar of the target face according to the template coefficient and at least two virtual face feature templates associated with the at least two real face feature templates.

Abstract: Provided are an offline teaching device and a measurement control device. The offline teaching device detects a shape of a measured object by a three-dimensional sensor unit, generates measurement procedure information in which measurement items are respectively associated with measurement points sequentially specified to the detected shape, and causes a measurement procedure information storage unit to store the measurement procedure information associated.

Abstract: A method for detecting and modelling of an object on a surface of a road by first scanning the road and generating a 3D model of the scanned road (which 3D model of the scanned road contains a description of a 3D surface of the road) and then creating a top-view image of the road. The object is detected on the surface of the road by evaluating the top-view image of the road. The detected object is projected on the surface of the road in the 3D model of the scanned road. The object projected on the surface of the road in the 3D model of the scanned road is modelled.

Abstract: A method of deferred vertex attribute shading includes computing, at a graphics processing pipeline of a graphics processing unit (GPU), a plurality of vertex attributes for vertices of each primitive of a set of primitives. The plurality of vertex attributes to be computed includes a vertex position attribute and at least a first non-position attribute for each primitive. One or more primitives of the set of primitives that do not contribute to a rendered image are discarded based upon the vertex position attribute for vertices of the set of primitives. A set of surviving primitives is generated based on the culling and deferred attribute shading is performed for at least a second non-position attribute for vertices of the set of surviving primitives.

Abstract: A file generation apparatus generates a file which includes material data used for generation of a virtual viewpoint image that is based on a multi-viewpoint image and type information for specifying a type of the material data, and outputs the generated file.

Abstract: A vessel network mesh and a tool mesh can be created for every frame of the gaming application. The simulated fluoroscopic x-ray image can be rendered using vessel network meshes and a pixel shader.

Abstract: Various implementations disclosed herein include devices, systems, and methods that generate floorplans and measurements using a three-dimensional (3D) representation of a physical environment generated based on sensor data.

Abstract: Provided is method and system for organizing a virtual showroom with one or more 3d images. Scripts are generated from the input images provided by the user, for generating 3D images of the products in the showroom. The generated 3D images can be in folded form, hanger display or mannequin.

Abstract: An extended reality (XR) support system establishes a communicative link between an XR presentation system and a multi-access edge compute (MEC) system operating on a cellular network. The XR support system identifies a parameter associated with a computing task to be performed in connection with an XR experience presented by the XR presentation system. The XR support system also identifies a condition associated with a capability of the XR presentation system or the MEC system to perform the computing task. Based on the identified parameter and the identified condition, the XR support system selects at least one of the XR presentation system or the MEC system to perform the computing task and then directs the selected system to perform the computing task. Corresponding methods and systems are also disclosed.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for rendering a three-dimensional virtual object in a video clip. The method and system include capturing, using a camera-enabled device, video content of a real-world scene and movement information collected by the camera-enabled device during capture of the video content. The captured video and movement information are stored. The stored captured video content is processed to identify a real-world object in the scene. An interactive augmented reality display is generated that: adds a virtual object to the stored video content to create augmented video content comprising the real-world scene and the virtual object and adjusts, during playback of the augmented video content, an on-screen position of the virtual object within the augmented video content based at least in part on the stored movement information.

Abstract: The disclosed computer-implemented method may include acquiring, from a client device within a real-world environment, information representative of the real-world environment, and transmitting the information representative of the real-world environment to a relocalization service. The method may further include receiving, from the relocalization service, (1) an anchor point that may include a mapped position within the real-world environment, and (2) a determined position within the real-world environment of a client device relative to the mapped position of the anchor point. The method may further include sending an identifier of the anchor point to an asset management service, and obtaining, from the asset management service, a digital asset. The method may further include presenting the digital asset at a position within an artificial environment relative to the mapped position of the anchor point. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An illustrative content augmentation system identifies a presentation context dataset indicating how an extended reality (XR) presentation device is to present XR content in connection with a presentation of primary content. Based on the presentation context dataset, the content augmentation system selects a subset of secondary content items from a set of secondary content items each configured for presentation as XR content that augments the presentation of the primary content. The content augmentation system also provides the selected subset of secondary content items for presentation by the XR presentation device in connection with the presentation of the primary content. Corresponding methods and systems are also disclosed.

Abstract: Presenting a virtual object includes obtaining, by a first device, a first geometric representation and a second geometric representation corresponding to a physical surface in a real environment, determining an initialization location on the first physical surface for a virtual object, obtaining a first normal for the first representation and a second normal for the second representation at the initialization location, and rendering the virtual object at the initialization location based on the first normal and the second normal.

Abstract: In one embodiment, a method includes reconstructing a three-dimensional shape of a target object, creating a two-dimensional normal map for the three-dimensional shape of the target object, accessing image data and depth data associated with the target object, generating a first normal data associated with the target object using the image data and the depth data, updating the normal map using the first normal data, and re-rendering the three-dimensional shape of the target object based on the updated normal map.

Abstract: The present specification discloses a method for displaying an AR navigation screen, and an AR navigation system. The method for displaying an AR navigation screen according to the present specification may comprise the steps of: overlapping and displaying images of the surroundings of a vehicle and a plurality of AR images corresponding to the images of the surroundings; generating a window for separately displaying a first area including AR images overlapping at least one of the plurality of AR images; and overlapping and displaying the window and the images of the surroundings. The invention of the present specification has the effect of improving user convenience and promoting safe vehicle operation by using a window when AR images and the like are difficult to recognize due to being overlapped.

Abstract: The present disclosure relates to the field of image analysis, in particular, it relates to a method for generating a virtual scene of objects. The disclosure also relates to a device comprising circuitry configured to carry out the method. The disclosure also relates to a computer program product adapted to carry out the method.

Abstract: Systems and methods are described to enable the creation of user interfaces that may adapt to different environments and may be automatically created. User interfaces may be two-dimensional or three-dimensional and may be used in virtual reality or augmented reality applications. An interface creator may create or receive digital assets associated with a content item, define virtual planes and associated digital asset templates, associate the digital assets with the virtual planes, and enable display of the virtual planes with associated digital assets to a user for user interaction. Digital assets may be automatically edited to meet the specifications of the templates associated with the virtual planes. Virtual planes and templates may also be standardized and aggregated so that a completed user interface may be easily delivered and presented with other content items in a uniform manner.

Abstract: An example system includes a first and second digital device. The first digital device may be configured to provide an interface displaying an image including a depiction of an object, place a bounding shape around the object, and crop contents of the bounding shape to create a portion. The second digital device may be configured to receive the portion, retrieve high-level features and low-level features, apply first Atrous Spatial Pyramid Pooling (ASPP) to the high-level features to aggregate the high-level features as aggregate features, concatenate results to create the aggregate features, up-sample, apply a convolution to the low-level features, concatenate the aggregate features with the low-level features after convolution to form combined features, segment the combined features to generate a polygonal shape outline along outer boundaries of the first object, and provide the first polygonal shape outline to the first digital device for display.

Abstract: Image processing techniques are described to obtain an image from a camera located on a vehicle while the vehicle is being driven, cropping a portion of the obtained image corresponding to a region of interest, detecting an object in the cropped portion, adding a bounding box around the detected object, determining position(s) of reference point(s) on the bounding box, and determining a location of the detected object in a spatial region where the vehicle is being driven based on the determined one or more positions of the second set of one or more reference points on the bounding box.

Abstract: A system may be configured to accurately track shelf activity in real-time with support for dynamic shelf size, configuration, and item containment. In some aspects, the system may parse regions of a video frame to determine a region of interest representation corresponding to a physical location (e.g., a shelf compartment), determine an enhanced region of interest representation based at least in part on the region of interest representation and an image enhancement pipeline, determine edge information of one or more objects based on the enhanced region of interest representation, compare a reference representation of the physical location to the edge information, and determine the amount of available space for the physical location based on the comparing.

Abstract: A display control unit displays a medical image from which at least one region of interest is extracted on a display unit. A correction unit corrects a boundary of the region of interest according to a correction instruction for the boundary of the region of interest extracted from the displayed medical image. An image generation unit generates a weighted image in which each pixel in the medical image has, as a pixel value of each pixel, a weight coefficient representing a weight of being within the region of interest, by setting an initial weight coefficient for the extracted region of interest and setting a corrected weight coefficient for a corrected region for which the correction instruction is given in the medical image.

Abstract: Disclosed are an object detection device and a control method. A method for controlling an object detection device comprises the steps of: receiving one image; dividing the received image into a predetermined number of local areas on the basis of the size of a convolutional layer of a convolution neural network (CNN); identifying small objects at the same time by inputting a number of the divided local areas corresponding to the number of CNN channels to each of a plurality of CNN channels; sequentially repeating the identifying of the small objects for each of the remaining divided local areas; selecting MM mode or MB mode; setting an object detection target area corresponding to the number of CNN channels on the basis of the selected mode; and detecting the small objects at the same time by inputting each set object detection target area to each of the plurality of CNN channels.

Abstract: The invention relates to a system for detecting objects in a digital image. The system comprises a neural network which is configured to generate candidate windows indicating object locations, and to generate for each candidate window a score representing the confidence of detection. Generating the scores comprises: generating a latent representation for each candidate window, updating the latent representation of each candidate window based on the latent representation of neighboring candidate windows, and generating the score for each candidate window based on its updated latent representation The invention further relates to a system for rescoring object detections in a digital image and to methods of detecting objects and rescoring objects.

Abstract: A determination system includes an imaging data acquisition device that captures an image of a printed surface of a printed product to acquire imaging data of the captured image, and a determination device that determines a printing method used to produce the printed surface of the printed product for capturing an image by the imaging data acquisition device. The determination device selects a determination area included in the captured image, extracts a determination end image from a portion around an end portion of a black determination image included in the determination area, acquires difference data that is a difference in gradation between two colors among gradation data of RBG colors of the extracted determination end image, acquires a determination value for determining a printing method used to produce the printed surface of the printed product, and determines a printing method used to produce the printed surface of the printed product.

Abstract: An image processing method includes analyzing multiple images data based on Illumination-invariant Feature Network (IF-NET) with an image processing device to generate corresponding sets of eigenvector, in which image data includes a first image data related to at least one first feature of the sets of eigenvector, and a second image data related to at least one second feature of the sets of eigenvector; choosing a corresponding first training set of tiles and second training set of tiles from the first image data and second image data with an image processing device based on IF-NET, and computing on both training set of tiles to generate a least one loss value; and adjusting IF-NET based on a least one loss value. An image processing system is also disclosed herein.

Abstract: An anomaly detection apparatus extracts a circumstantial feature value for anomaly detection corresponding to a circumstantial feature value for learning from other modal signal for anomaly detection different in modal from acoustic, calculates a signal pattern feature related to an acoustic signal of anomaly detection target based on the acoustic signal of anomaly detection target, the circumstantial feature value for anomaly detection and a signal pattern model learned based on an acoustic signal for learning and the circumstantial feature value for learning calculated from other modal signal for learning, and calculates an anomaly score for performing an anomaly detection of the acoustic signal of anomaly detection target based on the signal pattern feature.

Abstract: Aspects of the disclosure include computer-implemented methods and systems for providing generative adversarial network (GAN) digital image data. GAN digital image data corresponding to a suggested transaction for an identified customer can be determined.

Abstract: Disclosed is a method for recognizing a marine object based on hyperspectral data including collecting target hyperspectral data; preprocessing the target hyperspectral data; and detecting and identifying an object included in the target hyperspectral data based on a marine object detection and identification model, trained through learning of the detection and identification of the marine object. According to the present invention, the preprocessing and processing of the hyperspectral data collected in real time according to a communication state may be performed in the sky or on the ground.

Abstract: Systems and methods may make exchanging data in a neural network (NN) during training more efficient. Exchanging weights among a number of processors training a NN across iterations may include sorting generated weights, compressing the sorted weights, and transmitting the compressed sorted weights. On each Kth iteration a sort order of the sorted weights may be created and transmitted. Exchanging weights among processors training a NN may include executing a forward pass to produce a set of loss values for processors, transmitting loss values to other processors, and at each of the processors, performing backpropagation on at least one layer of the NN using loss values received from other processors.

Abstract: Systems and methods for optical character recognition using specialized confidence functions. An example method comprises: receiving a grapheme image; computing a feature vector representing the grapheme image in a space of image features; and computing a confidence vector associated with the grapheme image, wherein each element of the confidence vector reflects a distance, in the space of image features, between the feature vector and a center of a class of a set of classes.

Abstract: In one embodiment, a method includes receiving a user query associated with dialog-intents at a client system, executing tasks corresponding to the dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the tasks, wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and presenting the multi-perspective response at the client system.

Abstract: Machine learning based models recognize objects in images. Specific features of the object are extracted from the image using machine learning based models. The specific features extracted from the image assist deep learning based models in identifying subtypes of a type of object. The system recognizes the objects and collections of objects and determines whether the arrangement of objects violates any predetermined policies. For example, a policy may specify relative positions of different types of objects, height above ground at which certain types of objects are placed, or an expected number of certain types of objects in a collection.

Abstract: In establishment of a general-purpose artificial intelligence system, the machine simulates similarity, repeatability and adjacency of information, and stores the demand, award/penalty and emotion symbols together with related low-level features as a preset relation network. When the machine encounters input information, the machine iteratively identifies low-level features in the input information and stores them in a memory according to a simultaneous storage method. With the low-level features as nodes and the similarity, repeatability and adjacency relations between nodes as connection relations, the machine establish relations between the low-level features and the demand, award/penalty and emotion symbols to extend the relation network.

Abstract: An example apparatus includes a feature extractor to generate a first image descriptor based on a first image of a first retail product tag corresponding to a first category, the first image descriptor representative of one or more visual features of the first retail product tag; a feature descriptor generator to generate a feature descriptor corresponding to the first retail product tag by concatenating the first image descriptor and a first category signature corresponding to the first retailer category; and a classifier to generate a first probability value corresponding to a first type of promotional product tag and a second probability value corresponding to a second type of promotional product tag based on the feature descriptor; and determine whether the first retail product tag corresponds to the first type of promotional product tag or the second type of promotional product tag based on the first and second probability values.

Abstract: Methods, devices, and systems for identifying charging devices are provided. In one aspect, a method of identifying a charging device include: capturing an infrared image and a depth image of a current field of view with a depth camera; determining, according to the infrared image, that there are one or more suspected charging device areas that satisfy first specified conditions; determining, according to the depth image, that there is a target charging device area whose height relative to a depth camera is within a specified range in the one or more suspected charging device areas; and identifying the charging device according to the target charging device area. The first specified conditions indicate that a gray-scale value of each of pixels in an area is greater than a second specified value, and a number of the pixels in the area is greater than a third specified value.

Abstract: Systems that search databases of videos or images to identify similar products in a given video or image of a product are disclosed. The content of the given video is represented by a feature vector used to measure the given video's similarity to either a video or an image. When the system is deployed to recognize particular fashion items in videos, some such videos are taken in uncontrolled settings, and as a result, may have low resolution, poor contrast, minimal focus, motion blur, or low lighting. By recognizing and removing poor quality video frames from the image recognition pipeline, associating products across video frames to form tracklets of each product, and enriching the feature representation of each item for best retrieval result by fusing information from multiple video frames depicting the item, the system addresses the aforementioned shortcomings.

Abstract: A construction field management apparatus is wirelessly connected to a remote control vehicle with a surveying device for positioning the vehicle itself, a travel route is specified based on the position information in the coordinate system set in the work field, and a travel instruction based on the travel route, an instruction of performance of a predetermined function with the traveling, and are transmitted to the remote control vehicle, and the apparatus receives data based on the execution of the predetermined function from the remote control vehicle, and the construction field is managed by the construction field management apparatus for managing based on the received data.

Abstract: Techniques are described herein for using artificial intelligence to predict crop yields based on observational crop data. A method includes: obtaining a first digital image of at least one plant; segmenting the first digital image of the at least one plant to identify at least one seedpod in the first digital image; for each of the at least one seedpod in the first digital image: determining a color of the seedpod; determining a number of seeds in the seedpod; inferring, using one or more machine learning models, a moisture content of the seedpod based on the color of the seedpod; and estimating, based on the moisture content of the seedpod and the number of seeds in the seedpod, a weight of the seedpod; and predicting a crop yield based on the moisture content and the weight of each of the at least one seedpod.

Abstract: In some implementations, a device may receive image data identifying images of a space with racks and objects stored on the racks. The device may receive location data identifying location coordinates associated with the images. The device may process the image data and the location data to generate a merged point cloud identifying the racks and the objects in the space. The device may process the image data to generate mask data identifying at least a first mask for the racks and a second mask for the objects. The device may process the location data, the merged point cloud, and the mask data to generate a semantic point cloud identifying the racks and the objects in the space. The device may process the semantic point cloud, with a computer vision model, to calculate utilization metrics for the space.

Abstract: Augmented reality (AR) technology can be used to perform a real-time overlay on an image displayed on a user device. A user device can receive image data of an area comprising an item from the real-world. Based on the image data, an identity and a value of the item can be obtained by the user device. If the value of the item is greater than a pre-determined value for the item or a category of the item, then the user device can obscure in real-time on the displayed image the item or category of the item having the value that is greater than the pre-determined value.

Abstract: In one implementation, a method of defining a negative space in a three-dimensional scene model is performed at a device including a processor and non-transitory memory. The method includes obtaining a three-dimensional scene model of a physical environment including a plurality of points, wherein each of the plurality of points is associated with a set of coordinates in a three-dimensional space. The method includes defining a subspace in the three-dimensional space with less than a threshold number of the plurality of points. The method includes determining a semantic label for the subspace. The method includes generating a characterization vector of the subspace, wherein the characterization vector includes the spatial extent of the subspace and the semantic label.

Abstract: A method and system for an augmented reality assistant that recognizes a step in a product assembly process and assists in the installation of a constituent component into a base component. That system having a prepopulated database of templates, the templates being generated based off of two-dimensional images and the related three-dimensional models. The template database is used to train a first machine learning model, that model configured to identify the step in the product assembly process based on an image captured from an image capture device. Verifying that determination by a second machine learning model. Presenting an AR assistant to the user to assist with that step based on the related template.

Abstract: Implementations of the subject technology provide visualizations of non-visible features of a physical environment, at the location of the non-visible features in the physical environment. The non-visible features may include wireless communications signals, sounds, airflow, gases, subsonic and/or ultrasonic waves, hidden objects, or the like. A device may store visual contexts for visualizations of particular non-visible features. The device may obtain a depth map that allows the device to determine the location of the non-visible feature in the physical environment and to overlay the visualization on a user's view of that location. In this way, the non-visible feature can be visualized its correct location, orientation, direction and/or strength in the physical environment.

Abstract: Methods for automatically tagging one or more images and/or video clips using a audio stream are disclosed. The audio stream may be processed using an automatic speech recognition algorithm, to extract possible keywords. The image(s) and/or video clip(s) may then be tagged with the possible keywords. In some embodiments, the image(s) and/or video clip(s) may be tagged automatically. In other embodiments, a user may be presented with a list of possible keywords extracted from the audio stream, from which the user may then select to manually tag the image(s) and/or video clip(s).

Abstract: A computing system retrieves ball-by-ball data for a plurality of sporting events. The computing system generates a trained neural network based on ball-by-ball data supplemented with ball-by-ball data with ball-by-ball match context features and personalized embeddings based on a batsman and a bowler for each delivery. The computing system receives a target batsman and a target bowler for a pitch to be delivered in a target event. The computing system identifies target ball-by-ball data for a window of pitches preceding the to be delivered pitch. The computing system retrieves historical ball-by-ball data for each of the target batsman and the target bowler. The computing system generates personalized embeddings for both the target batsman and the target bowler based on the historical ball-by-ball data. The computing system predicts a shot type for the pitch to be delivered based on the target ball-by-ball data and the personalized embeddings.