32 results about "3d geometry" patented technology

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.

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.

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.

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.

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.

Generating a rendered image comprises: generating 904 a segmentation mask for an input 3D geometry; generating a plurality of texture maps associated with portions of the geometry; generating 906 a pl

In an example method, an NWM molding blank comprising a nonwoven material held compressed by an adhesive is placed in a separable mold and heated to a melting temperature of the adhesive. The molding blank expands, shaping into an NWM molded object having a 3D geometry as an intermediate NWM object. The intermediate NWM object is cooled through a temperature band having an upper boundary and a lower boundary, and further cooled to a solidification temperature of the adhesive. The upper boundary is above the solidification temperature and the lower boundary is below the adhesive melting temperature. While in the temperature band, the mold is separated so that exposed surfaces of the intermediate NWM object are accessible. The object is then transported to a contoured forming surface of a forming bed by an actuatable arm having an end effector that grips the exposed surfaces via vacuum suction, the object is lifted from the mold and placed on the contoured forming surface. Optionally, the end effector contacting surfaces include final forming features. The actuatable arm compresses the intermediate NWM object against the contoured forming surface and, optionally, the end effector final forming features, and continues compression until cooled to the solidification temperature.

A system and method for viewing aerial imagery and derived content on a web-based imagery browser that can be accessed by at least two users simultaneously. In addition, a system for interactively generating 3D geometry data for a location imaged from multiple viewpoints.

Systems and methods for 3D image scanners for real-time dynamic 3D surface imaging are disclosed. Embodiments of the present systems and methods describe a system and method comprising a first and / or second camera, and a projector, and a processor, the projector projects structured light with a fringe pattern onto a 3D object, the processor is configured to extract a phase map and a texture image from the image, and the processor calculates depth information from the phase map. Embodiments further describe methods and systems to determine wrapped phase from the image using a Hilbert transform, and to generate absolute phase from the wrapped phase using a combination of a quality-guided path following algorithm, a two-wavelength phase unwrapping algorithm, or a Markov Random Field method, and to generate a phase map from the absolute phase to determine depth information of the 3D object. Algorithms using conformal mapping, optimal transport mapping, and Tschupmueller mapping are used to register and track captured 3D geometry surfaces.

Systems, methods, and apparatuses for controlling a robot including a manipulator, including: determining three-dimensional (3D) geometry information about a target object based on an image of the target object; determining 3D geometry information about a scene in which the target object is to be placed based on at least one image of the scene; obtaining affordance information by providing the 3D geometry information about the target object and the 3D geometry information about the scene to at least one neural network model; commanding the robot to grasp the target object using the manipulator according to a grasp orientation corresponding to the affordance information; and commanding the robot to position the manipulator according to a placement direction corresponding to the affordance information in order to place the target object at a location in the scene.

The present invention provides a method for aligning a 2D image and a floor plan based on 3D geometry, comprising: (a) acquiring a 2D image taken through a camera installed in a specific space; and an image alignment device aligning the 2D image and the floor plan based on a neural network geometry estimation model. (b) generating an image 3D coordinate system by extending the 2D image into a 3D space with reference to 3D coordinate values ​​for each pixel of the 2D image inferred through a 3D model, and generating a floor plan 3D coordinate system by extending the 2D image into 3D space with a plane of the floor plan for the specific space as a floor plane; (b) generating alignment information between the image 3D coordinate system and the floor plan 3D coordinate system with reference to plane correspondence information between a first plane recognized in the image 3D coordinate system and a second plane in the floor plan 3D coordinate system corresponding to the first plane, and line correspondence information between 3D points in the image 3D coordinate system and 2D points in the floor plan 3D coordinate system corresponding to the 3D points; and (c) performing alignment between the 2D image and the floor plan by projecting each of the pixels of the 2D image onto the floor plan with reference to the alignment information.

The invention concerns a method (1) to detect deformations of, and / or damages to, structures permanently arranged on the earth's surface. In particular, said method (1) comprises: acquiring (11) georeferencing data indicative of geographical reference positions of predefined points of interest of a given structure to be monitored permanently arranged on the earth's surface, wherein said predefined points of interest are representative of a 3D geometry of the given structure without deformations and damages; acquiring (12) a SAR image of an area of the earth's surface where the given structure is arranged, wherein said SAR image is associated with a given reference coordinate system; transforming (13) the geographical reference positions of the predefined points of interest into corresponding expected positions in the given reference coordinate system associated with the acquired SAR image so as to carry out a reprojection of the 3D geometry of the given structure without deformations and damages on the acquired SAR image; identifying (14) in the acquired SAR image the predefined points of interest of the given structure; determining (15) actual positions in the given reference coordinate system associated with the acquired SAR image of the predefined points of interest identified in said SAR image; making a comparison (16) between the expected positions of the predefined points of interest and the corresponding actual positions in the acquired SAR image; and detecting (17) one or more deformations of, and / or one or more damages to, said given structure on the basis of the comparison made.

Rendering 3D geometry involves processing a very large amount of geometry. Compression techniques can be used to decrease the amount of data required for such geometry overall. A particular compression format for geometry is dense compression format, in which triangle strips are represented in highly compacted code sequences. In particular, compression code sequences describe the connectivity between triangles of a strip, thus ultimately provide a compact representation of which vertex indices comprise each triangle. A vertex index is an index into a vertex buffer that stores the actual vertex data, allowing for deduplication of such data. Though compact, such compression code sequences are somewhat tricky to decompress. A technique is provided herein for decompressing such code sequences. In particular, the technique involves a series of bitwise, arithmetic, and / or logical operations that expand out the code sequences into indices for the triangles.

A method is provided for using Light-Field Dynamic Homography (DH) to generate a large virtual focal plane from a non-rigid camera array with narrow overlaps between their fields of view (FOV). The method incorporates the 3D geometry of the cameras and employs non-linear least square optimization to dynamically estimate the inter-view homography transformations. Remarkably, only two feature correspondences are required between adjacent views to stitch the images and generate a wide virtual focal plane array, eliminating the need for significant FOV overlaps between the multiple cameras.

A method includes obtaining scan data of a dental object at a local device, wherein the scan data includes primary scan data, wherein the scan data includes secondary scan data indicative of characteristics other than the 3D geometry of the dental object. The method includes establishing a connection between the local device and a remote computing device. The method includes obtaining a performance indicator by detecting a performance of the connection. The method includes, if the performance indicator exceeds a primary performance threshold, entering a full connection mode. The method includes, if the performance indicator is less than the primary performance threshold entering a partial connection mode.

In various embodiments, a dubbing application performs three-dimensional (3D) tracking of (1) the face of an actor within video frames of a first media content item to generate 3D geometry representing the face of the actor, and (2) the face of a dubber within video frames of a second media content item to generate 3D geometry representing the face of the dubber. The dubbing application also tracks the texture and lighting of the face of the actor in the first media content item. The dubbing application aligns the 3D geometry of the face of the dubber with the 3D geometry of the face of the actor. Then, the dubbing application performs neural rendering to generate dubbed video frames using a trained machine learning model, the aligned 3D geometry of the dubber, the texture and lighting of the face of the actor, and the video frames of the first media content.

This invention relates to an intelligent method for generating architectural plans that considers the indoor environment, comprising the following steps: 1) establishing a dataset of functional zoning and room topology relationships, and a dataset of functional rooms and traffic space figure-ground relationships; 2) training corresponding neural network models; 3) generating floor plan layouts; 4) generating functional floor plan layouts; 5) generating 3D geometry; 6) selecting a suitable scheme; 7) selecting the optimal scheme. This invention's intelligent method for generating architectural plans that considers the indoor environment solves the core problems of "complex existing constraints, difficulty in adapting to multiple objectives, and low design efficiency" in the renovation of industrial heritage, achieving an intelligent, efficient, and quantifiable technical solution for architectural plan design to overcome the aforementioned deficiencies in existing technologies.

This invention discloses a general-purpose multi-axis 3D printing surface slicing method based on geodesic distance fields. The method includes: establishing an initial geodesic distance scalar field based on a temperature diffusion method; combining the overhang constraints and collision constraints of the multi-axis printing equipment, performing localized overhang correction and tangential constraint smoothing on the initial distance scalar field; wherein, during correction, an iterative weighted Poisson direction guidance mechanism is proposed to quickly correct regions violating the maximum overhang angle while maintaining geometric continuity, ensuring the distance field gradient direction stably converges to a feasible direction field that satisfies printability; based on the smoothed scalar field, preset isoparameters are selected, and the corresponding isoparameter surfaces are extracted as target isoparameter surfaces, which are then used as the deposition surface for multi-axis 3D printing. This invention significantly reduces the risk of directional jumps between slice surfaces and collisions with nozzles or robotic arms, can be used for arbitrarily complex 3D geometries, and can meet the overhang constraints and collision avoidance requirements of different printing equipment.

The invention relates to a building plane intelligent generation method considering an indoor environment. The building plane intelligent generation method comprises the following steps: 1) establishing a function partition and room topological relation data set and a function room and traffic space map base relation data set; 2) training a corresponding neural network model; 3) generating a plane layout diagram; 4) generating a plane function arrangement diagram; 5) generating a 3D geometry; 6) selecting a scheme meeting the requirements; according to the building plane intelligent generation method considering the indoor environment, the core problems that in industrial heritage transformation, current situation constraints are complex, multi-target adaptation is difficult, and design efficiency is low are solved, and the technical scheme that building plane design is intelligent, efficient and quantifiable is achieved so that the defects in the prior art can be overcome.

This disclosure provides a method for 3D reconstruction of a volleyball court and motion capture of athletes, applicable to the analysis of athlete-court interaction in volleyball scenarios. First, court reconstruction and camera estimation are performed: the 3D geometry of the court is reconstructed from the input volleyball video sequence, obtaining a 3D point cloud representation of the court and camera extrinsic parameter information. Then, athlete pose estimation is performed: through human body region detection and cropping in video frames, feature extraction, human keypoint localization and coordinate decoding, human pose parameter regression, and temporal consistency constraints, the 3D pose of the volleyball player is estimated. Finally, the volleyball court geometry and its global motion trajectory consistent with its spatial structure are output. By jointly modeling the volleyball court and athletes in 3D, a stable, continuous, and intuitively observable 3D motion process and scene structure can be obtained under a single video input condition, facilitating the analysis of volleyball techniques and their spatial relationships.

A method for enabling controller tracking in an augmented reality environment, and a system-non-temporary computer-readable medium are provided. [Solution] A method for creating a control from a 3D object includes registering object 135 as a controller, placing marker 115 on the object in association with a constellation, capturing the object along with the marker in image data, determining the 3D geometry from the image data, determining the location of the marker relative to the geometry, and registering the 3D object as a controller by associating the geometry with the marker location. The constellation is tracked in additional image data, and the motion characteristics of the controller are determined based on the orientation determined by the constellation, determining the orientation of the controller and using it for user input actions.

The invention discloses a 3D digital portrait automatic modeling system based on image feature fusion, and relates to the technical field of image data processing. The system comprises a multi-modal image acquisition module, an image preprocessing module, a layered feature extraction module, a dynamic weight feature fusion module, a 3D geometric reconstruction module, a detail optimization module and a model output module. The core of the method is that portrait multi-dimensional data is acquired through multi-modal image acquisition, color, texture and depth features are extracted in a layered manner after preprocessing, feature adaptive fusion is realized by adopting a dynamic weight algorithm, 3D geometric reconstruction and detail optimization are completed based on fused features, and finally a high-precision 3D digital portrait model is output. The system does not need a large amount of manual intervention, can solve the problems of rough feature fusion, detail loss and low automation degree in the prior art, remarkably improves the precision and efficiency of 3D portrait modeling, and is suitable for virtual fitting, film and television production and other scenes.

A method, machine learning model, and computer system are provided for simulation of a three-dimensional (3D) printer. An aspect of the method predicts the 3D printer output and provides feedback by: obtaining, in response to processing an input 3D geometry file in a simulation model for a 3D printer for simulating variations in printing parameters and their effect on the 3D printer output, an output 3D geometry file of a same file type as the input 3D geometry file and aligned to the input 3D geometry file; comparing the input 3D geometry file and the output 3D geometry file from the simulation model to determine differences; and displaying a representation of the differences to a user. Another aspect of the method provides the simulation model for a 3D printer for simulating variations in printing parameters and their effect on the 3D printer output; and trains the model with training dataset entries of combined training input data and training output data. The training input data is obtained as an input 3D geometry file as input into the 3D printer and the training output data is obtained by converting a 3D print output of the 3D printer generated in response to the input 3D geometry file into an output 3D geometry file of a same file type as the input 3D geometry file and aligning the output 3D geometry file and the input 3D geometry file.

A method for additive manufacturing of an object having a three-dimensional structure formed from a photo-curable material, the method implemented by a computing device comprising a processor and a computer readable medium having instructions executable by the processor, the method comprising at least the steps of: (a) rotating a vial containing the photo-curable material in a path of a light beam at a predefined rotation speed; (b) calculating patterns associated with a 3D geometry of the object; (c) modulating a focal length of the beam within the photo-curable material while projecting the beam comprising the patterns into the photo-curable material to form the object.

Provided is a framework for generating photorealistic 3D talking faces conditioned only on audio input. In addition, the present disclosure provides associated methods to insert generated faces into existing videos or virtual environments. We decompose faces from video into a normalized space that decouples 3D geometry, head pose, and texture. This allows separating the prediction problem into regressions over the 3D face shape and the corresponding 2D texture atlas. To stabilize temporal dynamics, we propose an auto-regressive approach that conditions the model on its previous visual state. We also capture face illumination in our model using audio-independent 3D texture normalization.

A linear cage deformer technique for multi-layer collocation is used to fit any 3D geometry to any target 3D geometry of a 3D avatar in a three-dimensional (3D) environment. For a multi-layer garment, the differences between consecutive garment layers are determined using an iterative process, and then the differences are accumulated to create a final superposition effect. Some embodiments relate to methods, systems, and computer readable media to provide such a 3D avatar worn with a multi-layer garment by providing an avatar having an avatar body in which an inner layer garment and an outer layer garment are to be overlaid. The inner-layer clothes can be overlaid on the body of the avatar, and the outer-layer clothes can be overlaid on the inner-layer clothes. Such overlay processes may include fitting the garment, and deforming the outer cage of the garment using linear cage deformer techniques. After superposition, an avatar body with the garments is rendered.

One embodiment of a method for generating scene representations includes processing a first image using a first trained machine learning model to generate one or more second images, processing the one or more second images using a second trained machine learning model to generate three-dimensional (3D) geometry and camera information, and generating a four-dimensional (4D) scene representation based on the 3D geometry and camera information.

Systems, methods, and apparatuses for controlling a robot including a manipulator, including: determining three-dimensional (3D) geometry information about a target object based on an image of the target object; determining 3D geometry information about a scene in which the target object is to be placed based on at least one image of the scene; obtaining affordance information by providing the 3D geometry information about the target object and the 3D geometry information about the scene to at least one neural network model; commanding the robot to grasp the target object using the manipulator according to a grasp orientation corresponding to the affordance information; and commanding the robot to position the manipulator according to a placement direction corresponding to the affordance information in order to place the target object at a location in the scene.

In various embodiments, a dubbing application performs three-dimensional (3D) tracking of (1) the face of an actor within video frames of a first media content item to generate 3D geometry representing the face of the actor, and (2) the face of a dubber within video frames of a second media content item to generate 3D geometry representing the face of the dubber. The dubbing application also tracks the texture and lighting of the face of the actor in the first media content item. The dubbing application aligns the 3D geometry of the face of the dubber with the 3D geometry of the face of the actor. Then, the dubbing application performs neural rendering to generate dubbed video frames using a trained machine learning model, the aligned 3D geometry of the dubber, the texture and lighting of the face of the actor, and the video frames of the first media content.

A computer-implemented method for facilitating 3D intraoral scanning using cloud computing is disclosed. The method includes obtaining, at a local device, scan data of a dental object, wherein the scan data includes primary scan data indicative of a 3D geometry of the dental object of a patient, wherein the scan data includes secondary scan data indicative of one or more characteristics other than the 3D geometry of the dental object; establishing a connection between the local device and a remote computing device; obtaining a performance indicator by detecting a performance of the connection; evaluating the performance indicator and based on the evaluation, entering a full connection mode if the performance indicator exceeds a primary performance threshold, wherein the full connection mode includes transmitting the scan data from the local device to the remote computing device, receiving at the local device from the remote computing device a digital representation of the dental object computed from the transmitted scan data, and displaying the digital representation; entering a partial connection mode if the performance indicator is less than the primary performance threshold.