-
公开(公告)号：US12175162B2
公开(公告)日：2024-12-24
申请号：US16984406
申请日：2020-08-04
Applicant: Apple Inc.
Inventor： Angela Blechschmidt , Daniel Ulbricht , Omar Elafifi
Abstract: 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.
-
公开(公告)号：US20230394773A1
公开(公告)日：2023-12-07
申请号：US18330652
申请日：2023-06-07
Applicant: Apple Inc.
Inventor： Angela Blechschmidt , Gefen Kohavi , Daniel Ulbricht
CPC classification number: G06T19/006 , G06T2200/24 , G06T15/10
Abstract: Generating a virtual representation of an interaction includes determining a potential user interaction with a physical object in a physical environment, determining an object type associated with the physical object, and obtaining an object-centric affordance region for the object type, wherein the object-centric affordance region indicates, for each of one or more regions of the object type, a likelihood of user contact. The object-centric affordance region is mapped to a geometry of the physical object to obtain an instance-specific affordance region, is used to render the virtual representation of the interaction with the physical object.
-
公开(公告)号：US11727606B2
公开(公告)日：2023-08-15
申请号：US17707774
申请日：2022-03-29
Applicant: Apple Inc.
Inventor： Ian M. Richter , Daniel Ulbricht , Jean-Daniel E. Nahmias , Omar Elafifi , Peter Meier
IPC: G06T11/00 , G06F3/04883
CPC classification number: G06T11/00 , G06F3/04883 , G06T2200/24
Abstract: In one implementation, a method includes: obtaining a user input to view SR content associated with video content; if the video content includes a first scene when the user input was detected: obtaining first SR content for a first time period of the video content associated with the first scene; obtaining a task associated with the first scene; and causing presentation of the first SR content and a first indication of the task associated with the first scene; and if the video content includes a second scene when the user input was detected: obtaining second SR content for a second time period of the video content associated with the second scene; obtaining a task associated with the second scene; and causing presentation of the second SR content and a second indication of the task associated with the second scene.
-
公开(公告)号：US20220256249A1
公开(公告)日：2022-08-11
申请号：US17729462
申请日：2022-04-26
Applicant: Apple Inc.
Inventor： Ian M. Richter , Daniel Ulbricht , Eshan Verma
IPC: H04N21/81 , G06V20/20 , G06T19/00 , H04N21/44 , H04N21/845
Abstract: In one implementation, consumption of media content (such as video, audio, or text) is supplemented with an immersive synthesized reality (SR) map based on the media content. In various implementations described herein, the SR map includes a plurality of SR environment representations which, when selected by a user, cause display of a corresponding SR environment.
-
5.发明授权公开(公告)号：US11386653B2
公开(公告)日：2022-07-12
申请号：US16961835
申请日：2019-01-18
Applicant: Apple Inc.
Inventor： Ian M. Richter , Daniel Ulbricht , Jean-Daniel E. Nahmias , Omar Elafifi , Peter Meier
Abstract: In one implementation, a method includes: identifying a first plot-within a scene associated with a portion of video content; synthesizing a scene description for the scene that corresponds to a trajectory of the first plot-effectuator within a setting associated with the scene and actions performed by the first plot-effectuator; and generating a corresponding synthesized reality (SR) reconstruction of the scene by driving a first digital asset associated with the first plot-effectuator according to the scene description for the scene.
-
Patent Agency Ranking
公开(公告)号：US11238604B1
公开(公告)日：2022-02-01
申请号：US16789788
申请日：2020-02-13
Applicant: Apple Inc.
Inventor： Mohammad Haris Baig , Daniel Ulbricht
Abstract: A system and techniques that use one or more machine learning models to predict a dense depth map (e.g., of depth values for all pixels or at least more pixels than a sparse estimation source (e.g., SLAM)). In some implementations, the machine learning model includes two sub models (e.g., neural networks). The first machine learning model predicts computer vision data such as semantic labels and surface normal directions from an input image. This computer vision data will be used to add to or otherwise improve sparse depth data. Specifically, a second machine learning model takes the semantic labels and surface normal directions from and sparse depth data (e.g., 3D points) from a sparse point estimation source (e.g., SLAM) as inputs and outputs a depth map. The output depth map effectively densities the initial depth data (e.g., from SLAM) by providing depth data for additional pixels of the image.
-
公开(公告)号：US11188795B1
公开(公告)日：2021-11-30
申请号：US16665354
申请日：2019-10-28
Applicant: Apple Inc.
Inventor： Chen-Yu Lee , Daniel Ulbricht
Abstract: Methods and systems that train a neural network to classify inputs using a first set of labeled inputs corresponding to a source domain and adapt that neural network to classify inputs from another domain. The neural network includes a generator network and two or more classifier networks. The generator network is trained to receive inputs and generate features. The two or more classifier networks are trained to classify those features into classes to obtain class probability predictions. The neural network is adapted to a target domain, for example, by training the classifier networks to maximize a Wasserstein distance-based discrepancy between the class probability predictions of the classifier networks, by training the classifier networks to increase Wasserstein distance-based discrepancy or by training the generator network to minimize the Wasserstein distance-based discrepancy between the class probability predictions of the multiple classifier networks, or both.
-
公开(公告)号：US20210074031A1
公开(公告)日：2021-03-11
申请号：US16963308
申请日：2019-01-18
Applicant: Apple Inc.
Inventor： Ian M. Richter , Daniel Ulbricht , Jean-Daniel E. Nahmias , Omar Elafifi , Peter Meier
IPC: G06T11/00
Abstract: In one implementation, a method includes: while causing presentation of video content having a current plot setting, receiving a user input indicating a request to explore the current plot setting; obtaining synthesized reality (SR) content associated with the current plot setting in response to receiving the user input; causing presentation of the SR content associated with the current plot setting; receiving one or more user interactions with the SR content; and adjusting the presentation of the SR content in response to receiving the one or more user interactions with the SR content.
-
公开(公告)号：US10824864B2
公开(公告)日：2020-11-03
申请号：US16360732
申请日：2019-03-21
Applicant: Apple Inc.
Inventor： Daniel Ulbricht , Angela Blechschmidt , Mohammad Haris Baig , Tanmay Batra , Eshan Verma , Amit Kumar KC
Abstract: In one implementation, a method of generating a plane hypothesis is performed by a head-mounted device (HMD) including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method include obtaining a point cloud based on the image of the scene and generating an object classification set based on the image of the scene, each element of the object classification set including a respective plurality of pixels classified as a respective object in the scene. The method includes generating a plane hypothesis based on the point cloud and the object classification set.
-
10.发明申请公开(公告)号：US20190354799A1
公开(公告)日：2019-11-21
申请号：US16530694
申请日：2019-08-02
Applicant: Apple Inc.
Inventor： Daniel Ulbricht , Thomas Olszamowski
Abstract: The invention is related to a method of determining a similarity transformation between first coordinates and second coordinates of 3D features, comprising providing a first plurality of 3D features having first coordinates in a first coordinate system which is associated with a first geometrical model of a first real object, wherein the first plurality of 3D features describes physical 3D features of the first real object, providing a second coordinate system, providing image information associated with a plurality of images captured by at least one camera, for each respective 3D feature of at least part of the first plurality of 3D features, wherein the respective 3D feature is captured by at least two of the plurality of images, determining camera poses of the at least one camera in the second coordinate system while the at least two of the plurality of images are captured, determining for the respective 3D feature a second coordinate in the second coordinate system according to the at least two of the plurality of images and the camera poses, and the method further comprising determining a similarity transformation between the first coordinates and the second coordinates of the at least part of the first plurality of 3D features, wherein the similarity transformation includes at least one translation, at least one rotation, at least one scale and/or their combinations in 3D space.
-
-
-
-
-
-
-
-
-
Search Results
68
records
(took 0.021 seconds)
