Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

113 results about "3d geometry" patented technology

Neural head avatar construction from an image

Systems and methods are disclosed that animate a source portrait image with motion (i.e., pose and expression) from a target image. In contrast to conventional systems, given an unseen single-view portrait image, an implicit three-dimensional (3D) head avatar is constructed that not only captures photo-realistic details within and beyond the face region, but also is readily available for animation without requiring further optimization during inference. In an embodiment, three processing branches of a system produce three tri-planes representing coarse 3D geometry for the head avatar, detailed appearance of a source image, as well as the expression of a target image. By applying volumetric rendering to a combination of the three tri-planes, an image of the desired identity, expression and pose is generated.
Owner:NVIDIA CORP

A method and a system for collision avoidance of a 3D robotic concrete printer

The present invention concerns a system and a method for collision avoidance of a 3D robotic concrete printer, whereby the method comprises the steps of performing an application and / or manipulation process by executing instructions, such as based on G-Code, with a 3D robotic concrete printer by moving a tool in a path for applying and / or manipulating concrete material; and moving the tool in response to commands to a motion planner, said movement being assisted by a model-based collision prediction system, whereby the model-based collision-prediction system involves the steps of inferring and generating 3D geometries of concrete structures from applying and / or manipulating concrete structures by commanding the 3D robotic concrete printer, using the 3D geometries as a 3D collision model, which allow at any point in time to check if parts of the 3D robotic concrete printer would yield a collision when performing said movement; whereby the 3D collision model of the concrete structure is developed in parallel to the application and / or manipulation process and is updated in correspondence to the progress of the execution of the process instructions.
Owner:SYDDANSK UNIV +1

Three-dimensional reconstruction method based on pulse camera and electronic equipment

The invention discloses a three-dimensional reconstruction method based on a pulse camera and electronic equipment, and relates to the technical field of three-dimensional reconstruction. According to the method, the problems of insufficient spatial-temporal information modeling and inaccurate initial attitude estimation in pulse camera three-dimensional reconstruction in related technologies are effectively solved, the precision of a three-dimensional reconstruction model is improved, a three-dimensional scene with higher quality and more realistic sense can be generated, meanwhile, efficient alignment of pulse data and three-dimensional geometry is realized through joint optimization of a framework, and the accuracy of the three-dimensional reconstruction model is improved. And the overall robustness and generalization ability of the system are enhanced.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Method of real-time generation of 3D imaging

The present invention relates to a method of real-time generation of a 3D geometry of an object. The method comprises the steps of calibrating at least one RGB camera pair arranged to provide images of the object, receiving input images of the object from the at least on RGB camera pair, and performing a stereo reconstruction in a first hierarchical level using the input images. The stereo reconstruction step further comprises the steps of a) performing a ray marching operation in a first resolution on the input images to determine geometry positions along each view ray of the images; b) applying a uniqueness criterion to the geometry positions; c) determining a normal for each geometry position; d) performing a regularization operation based on the geometry positions and the respective normal, providing updated geometry positions; and e) performing an interpolation operation on the updated geometry positions and respective normal. The method further comprises repeating steps a) and c)-e) in at least one iteration in at least one ascending hierarchical level, wherein the resolution in the ray marching operation is doubled for each iteration, resulting in a geometry buffer for each of the at least one camera pair. The present invention further relates to a 3D image generation device and a system comprising such device.
Owner:DIMENSION STREAM LABS AB

A doppler-based non-invasive computational diagnostic method for personalized cardiology

ActiveUS20240407761A1Medical imagingOrgan movement/changes detectionDiseaseValvular disease
Described is a Doppler-based non-invasive computational diagnostic method for personalized cardiology of subjects (e.g., patients with valvular diseases in both pre and post intervention status). The method may be performed for determining dynamic behavior of an aortic valve of the subject, the aortic valve having multiple asymmetric valve leaflets. The method includes receiving Doppler echocardiography images of the subject; processing the received images to reconstruct a 3D geometry of the valve leaflets; determining transient pressure boundary conditions for the valve leaflets using a lumped parameter model specific to the subject; performing a first finite element simulation to determine one or more geometrical parameters for the valve leaflets; iteratively calibrating initial value of one or more material parameters for the subject; and performing a second finite element simulation, based on the calibrated one or more material parameters, to determine an indicator of the dynamic behavior of the aortic valve.
Owner:MCMASTER UNIV

Predictive coding of boundary geometry information for mesh compression

ActiveUS12154300B2Image enhancementImage analysisVertex (geometry)3d geometry
This disclosure relates to methods and systems for encoding or decoding a 3D mesh with predictive coding of boundary geometry information. The example decoding method includes receiving a coded bitstream comprising a geometry patch for a three-dimension mesh; extracting, from the coded bitstream, a reconstructed geometry image for the geometry patch comprising a set of points corresponding to a set of geometry coordinates for a boundary vertex in the three-dimension mesh; deriving based on the set of the geometry coordinates, a 3D geometry coordinate for the boundary vertex; obtaining a prediction residue for the boundary vertex; and reconstructing, by the device, geometry information of the boundary vertex based on the derived 3D geometry coordinate and the prediction residue.
Owner:TENCENT AMERICA LLC

Advanced rendering optimization techniques for 3D graphics

A method of implementing directional opacity handling in Gaussian splats is disclosed. An approximate representation of a scene is received. 3D geometry data is generated. The 3D geometry data includes an approximate position and normal of each splat in a set of splats in the scene. Directional opacity values are calculated for the set of splats based on an application of a machine-learning model trained to optimize values of splat parameters, the values including the directional opacity values. The calculated directional opacity values are applied to the set of splats to enhance processing of the set of splats.
Owner:UNITY TECH SF

Field of View Optimization for Generated 3D Content Moment Related to Captured Gameplay Video

A method for generating a view of an event in a video game is provided, including the following operations: capturing two-dimensional (2D) gameplay video generated from a session of a video game; analyzing the 2D gameplay video to identify an event occurring in a scene depicted in the 2D gameplay video and identifying one or more elements involved in said event; further analyzing the 2D gameplay video to determine 3D geometry of the scene; using the 3D geometry of the scene to generate a 3D video asset of the event that occurred in the gameplay video; generating a 2D view of the 3D video asset for presentation on a display, wherein generating said 2D view includes determining a field of view (FOV) to apply for the 2D view, the FOV being configured to include the elements involved in the event.
Owner:SONY INTERACTIVE ENTERTAINMENT LLC

Robot with smart trajectory recording

An embodiment includes a method of determining a collision-free space for a robotic welding system. The method includes fixing a location of a part to be welded in a 3D coordinate space of a robotic welding system. An arm of the robotic welding system is moved around the part within the 3D coordinate space. Data corresponding to positions and orientations of the arm in the 3D coordinate space are recorded as the arm is moved within the 3D coordinate space around the part. The data is translated to swept volumes of data within the 3D coordinate space. The swept volumes of data are merged to generate 3D geometry data representing a continuous collision-free space within the 3D coordinate space.
Owner:LINCOLN GLOBAL INC

Visual inspection and measurement method for reinforcing mesh

The present invention relates to the technical field of buildings, and in particular, to a visual inspection and measurement method for a reinforcing mesh, comprising the steps of: using an RGBD camera to perform data acquisition on a building site; performing Mask R-CNN instance segmentation on RGB, preliminarily identifying a workpiece, and segmenting a 2D workpiece from the background; converting the obtained 2D workpiece into a 3D point cloud on the basis of an intrinsic mapping relationship of the RGBD camera; and for on-site acquired data, obtaining a segmentation result of rebar details by means of FPFH feature matching with an offline model; and on the basis of an identified rebar point cloud, performing cylinder fitting to obtain the number of rebars within the field of view. According to the present invention, preliminary identification of rebars is performed on a 2D site image by means of Mask R-CNN instance segmentation, and then rebar 3D geometry is precisely identified by using FPFH feature consistency.
Owner:SHANGHAI ROBOT IND TECH RES INST CO LTD

Synthesizing sequences of 3D geometries for movement-based performance

A technique for generating a sequence of geometries includes converting, via an encoder neural network, one or more input geometries corresponding to one or more frames within an animation into one or more latent vectors. The technique also includes generating the sequence of geometries corresponding to a sequence of frames within the animation based on the one or more latent vectors. The technique further includes causing output related to the animation to be generated based on the sequence of geometries.
Owner:ETH ZURICH +1

Generation of Real-World Object from Captured Gameplay Video

A method for generating a physical object is provided, including: capturing two-dimensional (2D) gameplay video generated from a session of a video game; analyzing the 2D gameplay video to identify a virtual object depicted in the 2D gameplay video; further analyzing the 2D gameplay video to determine 3D geometry of the virtual object; using the 3D geometry of the object to generate a 3D model of the virtual object; storing the 3D model to a user account; using the 3D model to generate a physical object resembling the virtual object.
Owner:SONY INTERACTIVE ENTERTAINMENT LLC

Unsupervised volumetric animation

Unsupervised volumetric 3D animation (UVA) of non-rigid deformable objects without annotation learns the 3D structure and dynamics of the object only from a single view red / green / blue (RGB) video and decomposes the single view RGB video into semantically meaningful portions that can be tracked and animated. Using a 3D automatic decoder framework, the UVA model learns 3D geometry and partial decomposition of underlying objects from still or video images in a fully unsupervised manner via a microperspective n-point (PnP) algorithm pairing with a keypoint estimator. This allows the UVA model to perform 3D segmentation, 3D keypoint estimation, novel view synthesis, and animation. The UVA model may obtain animatable 3D objects from a single or several images. The UVA method also characterizes a space in which all objects are represented in their normative, animated ready form. Applications include creating a shot from an image or video of a social media application.
Owner:SNAP INC

Generation of 3D Video Content Moment from Captured Gameplay Video

A method for generating a three-dimensional (3D) content moment from a video game is provided, including the following operations: capturing two-dimensional (2D) gameplay video generated from a session of a video game; analyzing the 2D gameplay video to determine 3D geometry of a scene depicted in the 2D gameplay video; using the 3D geometry of the scene to generate a 3D video asset of a moment that occurred in the gameplay video; storing the 3D video asset to a user account.
Owner:SONY INTERACTIVE ENTERTAINMENT LLC

Object relationship estimation from a 3D semantic mesh

Implementations disclosed herein provide systems and methods that determine relationships between objects based on an original semantic mesh of vertices and faces that represent the 3D geometry of a physical environment. Such an original semantic mesh may be generated and used to provide input to a machine learning model that estimates relationships between the objects in the physical environment. For example, the machine learning model may output a graph of nodes and edges indicating that a vase is on top of a table or that a particular instance of a vase, V1, is on top of a particular instance of a table, T1.
Owner:APPLE INC

Illuminated multi-view sensing using 3D reconstruction for in-cabin applications

Optical sensors (e.g., cameras) and (e.g., IR) illumination sources may be distributed in an environment (e.g., an interior space such as a cabin or cockpit of an ego-machine) and synchronized to generate frames of sensor data, which may be used to reconstruct 3D geometry and / or 3D pose of an occupant, operator, or other object in the environment. For example, stereo vision may be used to generate one or more depth maps from image data generated using different cameras, the depth map(s) may be transformed into a 3D point cloud, and surface reconstruction may be applied to reconstruct the 3D geometry of surface(s) in the environment. A 3D pose, one or more keypoints (e.g., facial landmarks), or some other representation of the shape of the reconstructed surface(s) may be extracted from the reconstructed surface and used in one or more downstream tasks, such as driver and / or occupant monitoring tasks.
Owner:NVIDIA CORP

Training for multimodal conditional 3D shape geometry generation

One embodiment of the present invention sets forth a technique for training a machine learning model on a geometry generation task. The technique includes generating, via execution of a diffusion model, a first set of training output corresponding to a first set of three-dimensional (3D) geometries based on a first set of conditioning inputs associated with a first conditioning mode, and training the diffusion model based on a first set of loss values associated with the first set of training output. The technique further includes generating, via execution of the diffusion model and a first adapter model, a second set of training output corresponding to a second set of 3D geometries based on a second set of conditioning inputs associated with a second conditioning mode, and training the first adapter model based on a second set of loss values associated with the second set of training output.
Owner:DISNEY ENTERPRISES INC +1

View angle controllable continuous image generation system and method based on three-dimensional point cloud

The invention discloses a visual angle controllable continuous image generation system and method based on three-dimensional point clouds, and relates to the technical field of crossing of computer vision and graphics, the visual angle controllable continuous image generation system comprises a 3D geometric coding module, a condition rendering module and a video generation module, the 3D geometric coding module is used for constructing and updating dynamic 3D scene representation in real time, and the condition rendering module is used for rendering the dynamic 3D scene representation in real time; the condition rendering module is used for generating 2D rendering frames with geometric constraints, the video generation module completes video synthesis based on a diffusion model, and for continuous frame requirements, feature matching information is injected and cache is updated in a blocking manner by combining a ControlNet subnet. By means of a bidirectional projection mechanism, on the basis that 3D point cloud is rendered into 2D frames with holes through forward projection, 3D cache of the complemented RGB-D frames is reversely updated through reverse projection, dynamic balance of geometric consistency and content updating is ingeniously achieved, the content can be updated in time while the geometric structure of the generated image is kept accurate, and the image quality is improved. And the authenticity and the continuity of the image are enhanced.
Owner:DAYAN TECHNOLOGY (TONGXIANG) CO LTD

Optical depth estimation using segmentation and geometric priors for interior space monitoring systems and applications

In various examples, optical depth estimation for interior space monitoring systems and applications is disclosed. Absolute 3D depth estimates from monocular image data may be generated using a machine learning model using 3D geometry priors and a joint learning framework that combines depth estimation with object segmentation. Three-dimensional geometry priors provide surface-level information that enriches the model's understanding of the relevant spatial geometry and resolves scale ambiguity in monocular depth estimation within automotive in-cabin environments. The model may include a common (e.g., shared) encoder stage that outputs features extracted from an optical image sensor feed to separate decoder stages that include a depth estimation decoder and a segmentation decoder. Joint learning for depth estimation and segmentation tasks during training achieves a more nuanced understanding of the in-cabin environment, leading to significantly improved depth accuracy.
Owner:NVIDIA CORP

Illuminated multi-view sensing using 3D reconstruction for in-cabin applications

Optical sensors (e.g., cameras) and (e.g., IR) illumination sources may be distributed in an environment (e.g., an interior space such as a cabin or cockpit of an ego-machine) and synchronized to generate frames of sensor data, which may be used to reconstruct 3D geometry and / or 3D pose of an occupant, operator, or other object in the environment. For example, stereo vision may be used to generate one or more depth maps from image data generated using different cameras, the depth map(s) may be transformed into a 3D point cloud, and surface reconstruction may be applied to reconstruct the 3D geometry of surface(s) in the environment. A 3D pose, one or more keypoints (e.g., facial landmarks), or some other representation of the shape of the reconstructed surface(s) may be extracted from the reconstructed surface and used in one or more downstream tasks, such as driver and / or occupant monitoring tasks.
Owner:NVIDIA CORP

Image adjustment 3D content creation architecture based on 2D diffusion

The invention discloses an image adjustment 3D content creation architecture based on 2D diffusion, and relates to the technical field of diffusion models, and the architecture comprises a diffusion model which is composed of a plurality of cross attention blocks in a U-Net structure and supports effective fusion of various modes of texts, images and camera parameters. In the present invention, it is devoted to create 3D content using a potential diffusion model. The 3D geometry is not generated directly through a potential diffusion model, but a two-stage formula is employed. First, a potential diffusion model of view conditioned reflex is organized, and a multi-view image is synthesized with a monocular image and the outside of a camera as inputs. Next, a neural radiation field is trained using the synthesized multi-view image, which is easily optimized as volume rendering is differentiable. After the neural radiation field training is completed, a 3D geometric model is generated through an advancing cube algorithm applied to a density field. The framework eliminates the requirement for pairing 3D training data and does not require a large amount of computing resources.
Owner:THE INST OF AUTOMATION HEILONGJIANG ACADEMY OF SCI

Electronic apparatus and controlling method thereof

An electronic apparatus for training an AI (Artificial Intelligence) model to generate an image of an object based on an input pose comprises at least one processor including processing circuitry and memory storing instructions. The instructions, when executed by the at least one processor individually or collectively, cause the electronic apparatus to obtain a plurality of images for training the AI model, obtain training images including an object from the plurality of images, obtain at least one parameter corresponding to each of the training images, obtain 3D geometry information of the object based on the at least one parameter, obtain a spherical neural texture mapped with the 3D geometry information, obtain warping prediction information for the spherical neural texture, update the spherical neural texture based on the warping prediction information, and train the AI model based on the updated spherical neural texture.
Owner:SAMSUNG ELECTRONICS CO LTD

System and method of selecting a complementary image from a plurality of images for 3D geometry extraction

A digital processing system for, a method, implemented on a digital processing system of, and a non transitory machine readable medium containing instructions that when executed implement the method of: automatically selecting one or more complementary images from a set of provided images for use with triangulation and determination of 3D properties of a user-selected point or geometric feature of interest, such as information on the slope (also called the pitch) and one or more dimensions of a roof of a building. The one or more complementary images are selected automatically by using an optimality criterion, also called a complementarity criterion.
Owner:NEARMAP AUSTRALIA PTY LTD

Generation of 3D video content moment from captured gameplay video

PCT designated stage expiredWO2025029450A1Video gamesComputational scienceComputer graphics (images)
A method for generating a three-dimensional (3D) content moment from a video game is provided, including the following operations: capturing two-dimensional (2D) gameplay video generated from a session of a video game; analyzing the 2D gameplay video to determine 3D geometry of a scene depicted in the 2D gameplay video; using the 3D geometry of the scene to generate a 3D video asset of a moment that occurred in the gameplay video; storing the 3D video asset to a user account.
Owner:SONY INTERACTIVE ENTERTAINMENT LLC +1

Computer-aided design method, computer-aided design system and computer-readable medium for hybrid additive and subtractive manufacturing

A method, system, and apparatus for computer-aided design and manufacture of a physical structure using hybrid additive and subtractive manufacturing, including media-encoded computer program products, includes, in one aspect, a method comprising: obtaining data on the 3D geometry of a part; simulating at least a portion of a manufacturing process, said at least a portion including adding a first material in a first stage and removing a second material in a second subsequent stage, wherein the second material comprises a portion of the first material, removing the second material includes mixing between the materials added in the first and second stages, and simulating the thermal effects of adding and removing materials in the first and second stages; and adjusting the amount of said portion based on the simulation results to prevent the part from deviating from its three-dimensional geometry, said deviation resulting in insufficient material available for mixing.
Owner:AUTODESK INC

System and methods for 3D geometry evaluation using vertex distance from center and mesh triangle vertex distance hashing

The present invention provides improved systems and methods for 3D geometry evaluation using vertex distance from center and mesh triangle vertex distance hashing. The present invention allows the generation of a unique hash that is immune to scale, position, orientation, and being inverted along any axis. This allows for the ability to store a single unique hash for each reference geometry that is calculated in advance, generate the unique hash for a search geometry, and then search for matching hash values. The actual geometries do not have to be stored, and only one string value, the hash value, is being searched.
Owner:ADAMS MARCUS DAVID