16714results about "Image generation" patented technology

The present disclosure provides an underwater detection method for contact leakage of a tunnel joint of a dam culvert, including: obtaining an underwater image sequence of the culvert by an underwater robot; preprocessing and registering the underwater image sequence; extracting particle information appearing in the underwater image sequence based on the registered underwater image sequence; constructing a three-dimensional fluid velocity distribution map based on the particle information, and determining leakage situation according to the three-dimensional fluid velocity distribution map; and superimposing the three-dimensional fluid velocity distribution map on a preconfigured three-dimensional culvert model, and rendering and displaying it. The present disclosure can adapt to the complex and changeable underwater environment inside the culvert, it has a high sensitivity to fine leakage in the deep layer, it can realize the accurate measurement and trend prediction of leakage, and it can automate the detection process to reduce manual dependence.

Aspects of the present disclosure relate to systems, devices and methods for performing a surgical step or surgical procedure with visual guidance using a head mounted display with systems, techniques and methods for improving the accuracy of an augmented reality display and / or for enhancing the 3D visualization of an augmented reality display.

In some embodiments, a computer system changes a level of detail with which a respective environment is being displayed. In some embodiments, a computer system applies a neutralization adjustment to generate a representation of the physical environment. In some embodiments, a computer system displays a user interface object in a three-dimensional environment with a three-dimensional stereoscopic effect. In some embodiments, a computer system facilitates light blending. In some embodiments, a computer system transitions between three-dimensional environments using visual effects. In some embodiments, a computer system detects a movement in a viewpoint of a user while displaying a portal to a virtual environment, and either maintains or ceases display of the portal based on the amount of movement and / or a direction in which the portal opens. In some embodiments, a computer system outputs a different sound effect when initiating display of different virtual three-dimensional environments.

Approaches presented herein provide for the generation of a text-based representation of an environment. In particular, a large language model (LLM) can be used to generate a tokenized text string representation of an environment using information such as the semantics, topology, and geometry of the environment. A language model-generated representation can comply with real-world rules and constructs, and can account for omissions or errors in the input data based upon known relationships and semantics for various objects in the environment. Such representations can be used to generate reconstructions of existing environments, correct or augment previously-constructed representations, or generate representations of new but realistic environments that comply with real-world rules. A text-based representation can comprise a one-dimensional string of tokens, which can encapsulate the important spatial information and semantics of an environment.

An example operation may include one or more of training a generative artificial intelligence (GenAI) model to generate images based on user data using a dataset of images, executing the GenAI model based on input data from a user interface of a software application to generate an image corresponding to the input data, and displaying the image via a user interface of a software application, receiving feedback about the image via the user interface; andretraining the GenAI model based on the generated image and the received feedback about the image via the user interface.

The invention discloses a historical block scene three-dimensional reconstruction method and system based on Gaussian sputtering, and the method comprises the steps: collecting a historical block video sequence through a lightweight panorama camera, extracting a multi-frame panorama, and generating an image data set through a projection converter; monocular depth and normal estimation is carried out through a pre-training visual model, and a prior depth and normal graph data set of a historical block scene is constructed; sparse reconstruction is carried out on the multi-view image data set based on the SfM technology, initial point cloud and camera pose information are acquired, and a Gaussian ellipsoid is optimized in combination with prior depth and normal information; dynamically calculating the geometric width estimation value of the street, and guiding and adjusting the adaptive density of the Gaussian ellipsoids of the vertical surfaces on the two sides; rendering the optimized Gaussian ellipsoid through an improved rasterization renderer; and designing a multi-modal loss function and a regularization mechanism to optimize reconstruction and rendering results. According to the method, high-fidelity three-dimensional reconstruction of the historical block scene is realized, and the adaptability of the Gaussian sputtering method to the complex block scene is enhanced.

Aspects of the subject technology provide for human subject Gaussian splatting using machine learning. A method includes receiving a video input having a scene and a subject. The method also includes obtaining a three-dimensional (3D) reconstruction of the subject and the scene from the video input. The method includes generating a 3D Gaussian representation of each of the scene and the subject. The method also includes generating a deformed 3D Gaussian representation of the subject by adapting the 3D Gaussian representation of the subject to the 3D reconstruction of the subject. The method includes rendering a visual output comprising an animatable avatar of the subject and the scene using differentiable Gaussian rasterization based at least in part on the deformed 3D Gaussian representation of the subject and the 3D Gaussian representation of the scene.

Apparatuses, systems, and techniques are presented to generate digital content. In at least one embodiment, one or more neural networks are used to generate a three-dimensional voxel representation of a scene based, at least in part, upon a plurality of two-dimensional images of the scene.

The invention provides a construction scene prediction method and device fusing an image, a text and a BIM modal, and relates to the technical field of intelligent construction prediction management. According to the method, the BIM semantic graph is constructed by extracting the BIM semantic information of the BIM model, and the target detection recognition of the construction site video is carried out in combination with the YOLO model to obtain the target detection result; performing cross-modal alignment with the CLIP to realize deep fusion of the multi-modal data of the image, the text and the BIM to obtain a multi-modal heterogeneous graph; and inputting the multi-modal heterogeneous graph into a space-time sequence model for prediction, outputting prediction results of construction scenes at a plurality of moments in the future, and dynamically mapping the prediction results to a digital twinborn platform to realize risk early warning and visual display. The construction dynamic change can be captured in real time, the construction progress and risk can be accurately predicted, and the intelligent level of construction management is improved.

In various examples, systems and methods are disclosed relating to generation of four-dimensional (4D) content models, such as 4D content models to render realistic sequences of frames of 3D data. The systems can initialize a 3D component of the 4D content model, such as a 3D Gaussian splatting representation, based at least on a prompt for the 4D content. The system can configure motion and / or dynamics for the sequence of frames by evaluating frames rendered from the 4D content model using one or more latent diffusion models (LDMs), including a video LDM. The system can perform operations such as autoregressive generation of frames to create long sequences of content, motion amplification to facilitate realistic, dynamic motion generation, and regularization to facilitate generation of complex dynamics.

The invention relates to the technical field of building information models, augmented reality, synchronous localization and map construction, and provides a deep learning-based SLAM-BIM augmented reality cooperative localization method and system, and the method comprises the steps: introducing a Transform time sequence feature extractor and a geometric relation graph, evaluating a dynamic distribution weight through combining with the confidence, achieving the cross-modal closed-loop detection, and obtaining an SLAM-BIM augmented reality cooperative localization result. A lightweight semantic segmentation network and a feature fusion module are utilized, a dense map with consistent geometric semantics is constructed, a space-time error propagation equation is constructed, online calibration is realized by means of BIM scale prior, an incremental fusion algorithm is designed, a global pose is optimized in combination with AR interaction, and the system fuses SLAM visual trajectory features and BIM semantic geometric features through a deep learning technology. According to the method, the problems that traditional SLAM accumulative errors are large and the BIM fusion precision is low are solved, robust positioning and map construction in a complex scene are achieved, the cooperation precision and real-time performance of SLAM and BIM are improved, and the method is suitable for AR scenes such as building construction and operation and maintenance.

The invention provides a building construction monitoring method, which comprises the steps of obtaining multi-view video image data of a construction site, and performing fusion processing on the multi-view video image data by adopting an image splicing algorithm to obtain a panoramic three-dimensional scene model of the construction site; acquiring an image frame in the panoramic three-dimensional scene model, and analyzing the image frame by adopting a pre-trained work type identification model to obtain position information of operating personnel and equipment of each work type; acquiring position information of the operating personnel of each type of work, and analyzing postures of the operating personnel by adopting a pre-trained human body posture estimation model to obtain action state information of the operating personnel; and acquiring the position information and the action state information of the operating personnel of each type of work, and judging the specific operation state of the operating personnel of each type of work in combination with a pre-established work type operation knowledge base.

Image series transformation for optimal compressibility is performed with neural upsampling and error resilience. A novel correlation network composed of convolutional layers for feature extraction that extract multi-dimensional features from the image and a channel-wise transformer with attention to capture complex inter-channel dependencies. An angle optimizer enhances compressibility of an image and an error resilience subsystem improves robustness against transmission errors and data loss. The error resilience subsystem applies forward error correction coding, data partitioning based on importance, and embeds error concealment hints. This hybrid approach addresses both local and global features, mitigates compression artifacts, improves image quality, and enhances data integrity during transmission. The correlation network incorporates error correction and concealment techniques during decoding. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving information for accurate analysis.

Systems and methods are disclosed for evaluating a patient with vascular disease. One method includes receiving one or more vascular models associated with either the patient or with a plurality of individuals; receiving observed perfusion information associated with the patient; and estimating, using one or more computer processors, one or more blood flow characteristics or one or more pathological characteristics of the patient based on the observed perfusion information and the one or more vascular models.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify two-dimensional images via scene-based editing using three-dimensional representations of the two-dimensional images. For instance, in one or more embodiments, the disclosed systems utilize three-dimensional representations of two-dimensional images to generate and modify shadows in the two-dimensional images according to various shadow maps. Additionally, the disclosed systems utilize three-dimensional representations of two-dimensional images to modify humans in the two-dimensional images. The disclosed systems also utilize three-dimensional representations of two-dimensional images to provide scene scale estimation via scale fields of the two-dimensional images. In some embodiments, the disclosed systems utilizes three-dimensional representations of two-dimensional images to generate and visualize 3D planar surfaces for modifying objects in two-dimensional images. The disclosed systems further use three-dimensional representations of two-dimensional images to customize focal points for the two-dimensional images.

A method for mapping a three-dimensional (3D) point cloud model based on deep learning includes: extracting features of image data by using a convolutional neural network; extracting features of point cloud data by using a PointNet point cloud processing network, and constructing a 3D model of the point cloud data by using a triangular mesh; aligning the 3D model and an image spatially and temporally; performing projection mapping on the aligned 3D model and image, and superimposing location information in the point cloud data onto texture information of the image to obtain a first fused image; fusing the features of the point cloud data and the features of the image data to obtain a second fused image with a fused feature; and superimposing the first fused image onto the second fused image, and obtaining a superimposition weight by using the convolutional neural network, to generate a mapped 3D model.

A system comprises a processor and a memory having computer readable instructions stored thereon, which, when executed by the processor, cause the system to display an image of a surgical environment. The image includes an information icon corresponding to an instrument in the surgical environment. The instructions further cause the system to display an image of a body part of a user. The image of the body part is used to interact with the information icon. The instructions further cause the system to receive a gesture of the body part, via a gesture-based input device registering movement of the body part, to cause the image of the body part to interact with the information icon. The instructions further cause the system to display an information menu in the image of the surgical environment based on the interaction between the image of the body part and the information icon.

Methods for displaying and organizing user interfaces in a computer-generated environment provide for an efficient and intuitive user experience. In some embodiments, user interfaces can be grouped together into a container. In some embodiments, user interfaces can be added to a container, removed from a container, or moved from one location in the container to another location. In some embodiments, a visual indication is displayed before a user interface is added to a container. In some embodiments, a user interface can replace an existing user interface in a container. In some embodiments, when moving a user interface in a computer-generated environment, the transparency of a user interface that is obscured can be modified.

An example operation may include at least one of receiving, via a user interface of a device, an activation input from a user to initiate a session, capturing, by a camera of the device, a scan of a body of the user, wherein the capturing comprises recording at least one image and / or at least one video of the user, processing the at least one image and / or video to generate a three- dimensional model of the user comprising measurements and contours of the body, retrieving, from a database, at least one clothing item associated with the user, the at least one clothing item comprising dimensional attributes and texture attributes, rendering, by a graphics processing unit, the at least one clothing item onto the three-dimensional model to generate a visual representation, wherein the rendering simulates draping behavior, movement, and light interaction of the at least one clothing item relative to the three-dimensional model, and displaying, on the user interface, an interactive visualization comprising the visual representation of the three-dimensional model with the at least one clothing item from multiple viewing angles.

The invention discloses a surgical robot resection navigation method based on multi-modal image registration. The method comprises the following steps: acquiring a preoperative multi-modal medical image of a patient and reconstructing a three-dimensional model containing a focus and a dangerous structure; acquiring an intraoperative real-time image; extracting cross-modal invariant features from the pre-operative and intra-operative images by using a first deep learning network, and establishing an initial corresponding relation; predicting an initial non-rigid deformation field by using a second deep learning network, based on the pre-operative / intra-operative image and the initial corresponding relation and in combination with physical model constraints; tracking a surgical tool in real time, and updating a non-rigid deformation field in real time by adopting an incremental calculation strategy; applying the updated deformation field to the preoperative three-dimensional model to generate a deformed model; and mapping the tool position to the deformed model, and generating a navigation instruction. According to the method, soft tissue deformation can be accurately compensated, multi-modal image information is effectively fused, navigation information is dynamically updated in real time, and the precision and safety of robot surgery are remarkably improved.

Disclosed are systems and methods for generating a 3D model from a single 2D image, the method comprising: receiving a single 2D input image of an object; generating a set of consistent multi-view images based on the single 2D input image using a fine-tuned 2D diffusion model that processes multiple views together in a tiled configuration; constructing a 3D feature volume by projecting 2D patch features from the generated multi-view images using corresponding camera pose information; generating a 3D mesh using a pair of 3D diffusion networks conditioned on the multi-view images, wherein the pair of 3D diffusion networks comprises a first network for generating a coarse occupancy volume and a second network for generating a high-resolution sparse volume; and refining a texture of the generated 3D mesh to produce a textured 3D mesh.

A computer-implemented method of processing patient image data comprises: receiving a patient-specific vascular model of an individual, wherein the patient-specific vascular model is based at least in part on medical images acquired of the individual; receiving a patient-specific tissue model of a tissue of the individual; observing an actual perfusion value of the tissue; determining at least one vessel pathology that causes the actual perfusion value; and selecting a candidate updated vascular model of the plurality of candidate updated vascular models that results in a minimum difference between the hypothetical perfusion value and the actual perfusion value; updating the patient-specific vascular model to include the at least one vessel pathology of the selected candidate updated vascular model; and outputting an estimate of a location of the at least one vessel pathology or an estimate of a severity of the at least one vessel pathology.

The invention relates to the technical field of control and regulation systems, in particular to a hearth auxiliary regulation control system which comprises a data processing module, an analysis module, a control module, a regulation and control module, an optimization module and a safety early warning module. The data processing module collects temperature data of a hearth combustor area, a water cooling wall and a tail flue in real time through a distributed temperature sensor network, and a dynamic combustion field three-dimensional model is generated through Kalman filtering denoising, redundancy cross validation and a temperature compensation algorithm in combination with combustor flame position signals and an air door opening state. And the optimization module updates the strategy weight based on the combustion efficiency improvement rate, and reinforces learning to extend the adaptive boundary of the strategy library. And the safety early warning module calculates the matching coefficient of the pipe wall temperature and the allowable stress in real time, triggers a grading intervention strategy to reduce the overtemperature risk, forms full-process closed-loop control, and improves the thermal efficiency and the operation safety of the boiler.

The invention discloses a digital twin three-dimensional scene modeling method based on a webGPU, and relates to the technical field of three-dimensional scene modeling and graphic computing, multi-source sensing data are asynchronously sampled from sparse point cloud, a video texture sequence, a scene semantic tag graph and a structure boundary tuple, and a six-dimensional structure unit group is generated through a normalization operator; constructing a structural unit atlas with nodes representing component entities and edges representing constraint relations, and introducing a tension balance mechanism and multi-scale constraints to generate a modeling path prior model; constructing a graph calculation and graph rendering dual-channel assembly line in the WebGPU, and executing parallel texture mapping and boundary fitting operation; a dynamic sensing module is used for capturing scene disturbance and driving atlas response, and incremental reconstruction of the model is achieved; and finally, mapping the model to a Web terminal, and supporting microscopic semantic query and multi-layer data linkage. According to the method, the response speed, semantic consistency and structural adaptability of three-dimensional modeling in a complex environment are improved.

Techniques for generating one or more images of a space in one or more target styles using a generative machine learning model is described. Furnishing products similar to furnishings detected in the generated images are identified in a catalog of furnishing products and information about the identified furnishing products is provided to a user via a user interface. Also describes are techniques for generating modified images of a space using a generative machine learning model. Furnishing products similar to alternative furnishings in modified image are identified in the catalog of furnishing products and information about the identified furnishing products is provided to a user via a user interface.

Methods of generating three-dimensional (3D) views of a scene, such as a surgical scene, and associated systems and devices are disclosed herein. In some embodiments, a representative method includes moving a sensor array about a target volume and capturing RGB image data and depth data of the target volume with multiple cameras and a depth sensor of the sensor array, respectively. Poses of the RBG cameras and the depth sensor can be determined at each position. The captured RGB image data and the RGB camera poses can be used to train a radiance volume of a neural radiance field (NeRF) algorithm, and the depth data can be used to constrain the training of the NeRF algorithm. The NeRF algorithm can render a 3D image of the target volume based on a specified observer pose.

A computer-implemented method of providing a temporal sequence of 3D angiographic images (110) representing a flow of a contrast agent through a region of interest (120), is provided. The method includes: inputting (S130) volumetric image data (130a, 130b), and a temporal sequence of 2D angiographic images (140) into a neural network (NN1); and generating (S140) the predicted temporal sequence of 3D angiographic images (110) representing the flow of the contrast agent through the region of interest (120) in response to the inputting.

Methods and systems are described for 3D modeling and visualization of a patient's facial structure and features for dental treatment planning.

The invention relates to a cloth defect detection and classification method for garment production, and the method comprises the following steps: carrying out the localization of a cloth image in the space, and constructing a dynamic response model based on the texture continuity of a local region; segmenting the continuous cloth image into sliding windows; constructing a local texture response sequence on a time axis for each window; a dynamic response index DRI is used for describing the stability of the area in space and time, and the stability serves as the basis of anomaly judgment; detecting the position and the change track of the texture response mutation, and reasoning the boundary and the form of the flaw; capturing jump points of which the variation amplitude is greater than a set threshold value in the response sequence; deducing a shape boundary and a diffusion path in the image in combination with a sudden change trend between adjacent windows; constructing a sudden change trajectory diagram to describe the real form of the flaw; judging whether the area belongs to a real defect or not by analyzing the structural stability of the defect boundary, and forming a defect credibility index DCI; and calculating the direction consistency and the edge gradient stability of the flaw boundary.

An apparatus for generating a three-dimensional (3D) model of anatomical object via machine-learning, wherein the apparatus includes a process and a memory containing instructions configuring the processor to receive a set of images of an anatomical object pertaining to a subject, generate an 3D data structure representing the anatomical object as a function of the set of images using an anatomy modeling model, generate an initial 3D model of the anatomical object and refine the generated initial 3D model of the anatomical object as a function of the 3D data structure representing the anatomical object.