公开(公告)号：US20240362852A1

公开(公告)日：2024-10-31

申请号：US18770916

申请日：2024-07-12

申请人： Arm Limited

发明人： Richard BRUCE ,  William Robert STOYE ,  Mathieu Jean Joseph ROBART

IPC分类号： G06T15/06 ,  G06F16/901 ,  G06T15/00

CPC分类号： G06T15/06 ,  G06F16/9027 ,  G06T15/005 ,  G06T2210/21

摘要： An instruction (or set of instructions) that can be included in a program to perform a ray tracing acceleration data structure traversal, with individual execution threads in a group of execution threads executing the program performing a traversal operation for a respective ray in a corresponding group of rays such that the group of rays performing the traversal operation together. The instruction(s), when executed by the execution threads in respect of a node of the ray tracing acceleration data structure, cause one or more rays from the group of plural rays that are performing the traversal operation together to be tested for intersection with the one or more volumes associated with the node being tested. A result of the ray-volume intersection testing can then be returned for the traversal operation.

公开(公告)号：US20240355456A1

公开(公告)日：2024-10-24

申请号：US18617890

申请日：2024-03-27

申请人： GENGENAI, INC

发明人： Hojin Cho ,  Sangil Kim ,  Hoyeong Heo

IPC分类号： G16H30/40 ,  G06T11/00 ,  G06T15/00 ,  G16H30/20

CPC分类号： G16H30/40 ,  G06T11/00 ,  G06T15/00 ,  G16H30/20

摘要： Provided is a method for training a generative model for medical images associated with a plurality of body parts, which is performed by one or more processors and includes receiving training medical image data, acquiring label data associated with the training medical image data, and training a generative model for medical images based on the training medical image data and the acquired label data.

公开(公告)号：US20240355032A1

公开(公告)日：2024-10-24

申请号：US18436688

申请日：2024-02-08

申请人： Intel Corporation

发明人： Atsuo Kuwahara ,  Deepak S. Vembar ,  Chandrasekaran Sakthivel ,  Radhakrishnan Venkataraman ,  Brent E. Insko ,  Anupreet S. Kalra ,  Hugues Labbe ,  Abhishek R. Appu ,  Ankur N. Shah ,  Joydeep Ray ,  Elmoustapha Ould-Ahmed-Vall ,  Prasoonkumar Surti ,  Murali Ramadoss

IPC分类号： G06T15/00 ,  G06F9/50 ,  G06T15/04 ,  G06T15/80 ,  G06T17/10

CPC分类号： G06T15/005 ,  G06F9/5027 ,  G06T15/04 ,  G06T15/80 ,  G06T17/10 ,  G06T2215/16

摘要： An embodiment of an electronic processing system may include an application processor, persistent storage media communicatively coupled to the application processor, and a graphics subsystem communicatively coupled to the application processor. The graphics subsystem may include a first graphics engine to process a graphics workload, and a second graphics engine to offload at least a portion of the graphics workload from the first graphics engine. The second graphics engine may include a low precision compute engine. The system may further include a wearable display housing the second graphics engine. Other embodiments are disclosed and claimed.

公开(公告)号：US12125194B2

公开(公告)日：2024-10-22

申请号：US18107077

申请日：2023-02-08

申请人： Evident CORPORATION

发明人： Yohei Sakamoto

IPC分类号： G06T7/00 ,  G06T7/246 ,  G06T15/00 ,  H04N23/50

CPC分类号： G06T7/001 ,  G06T7/248 ,  G06T15/00 ,  G06T2207/10016 ,  G06T2207/10068 ,  G06T2207/30164 ,  G06T2207/30244 ,  H04N23/555

摘要： A three-dimensional data generation method includes the following processing. A processor acquires two or more images of a component inside a turbine. The processor detects two or more correspondence regions that are the same regions in at least two images. The processor determines whether at least part of a region of each image is a change region or a non-change region. The processor generates three-dimensional data by using a correspondence region determined to be the change region without using a correspondence region determined to be the non-change region.

公开(公告)号：US20240346741A1

公开(公告)日：2024-10-17

申请号：US18626411

申请日：2024-04-04

申请人： Mediatek Inc.

发明人： Chengping Luo ,  You-Ming Tsao ,  Bozhan Chen ,  Sheng-Wen Huang

IPC分类号： G06T15/00

CPC分类号： G06T15/005 ,  G06T2210/12

摘要： In aspects of the disclosure, a method, a system, and a computer-readable medium, are provided. The method for processing graphics data with a graphics rendering pipeline comprising a mesh shader and a tiler, comprising outputting, by the mesh shader in response to an input of the graphics data, legacy mesh shader output parameters including vertices and primitives, and additional data with a meshlet bounding-box, or axis-aligned bounding box (AABB) structure; sending the AABB to the tiler as an input, and generating, by the tiler, a visibility stream according to the AABB, wherein each entity of the visibility stream indicates that the AABB is fully visible, partially visible, or invisible in the view frustum; and sending the visibility stream back to the tiler as a further input along with the legacy mesh shader output parameters for coming rasterization in a fragment pass.

公开(公告)号：US20240346668A1

公开(公告)日：2024-10-17

申请号：US18634088

申请日：2024-04-12

申请人： THERAPANACEA ,  INSTITUT DE CANCEROLOGIE GUSTAVE ROUSSY ,  CENTRE LEON BERARD

发明人： Amaury LEROY ,  Eric DEUTSCH ,  Vincent GREGOIRE ,  Nikos PARAGIOS

IPC分类号： G06T7/30 ,  G06T7/00 ,  G06T7/11 ,  G06T15/00 ,  G06V10/74 ,  G16H30/40

CPC分类号： G06T7/30 ,  G06T7/0012 ,  G06T7/11 ,  G06T15/00 ,  G06V10/761 ,  G16H30/40 ,  G06T2207/20081 ,  G06T2207/30008 ,  G06T2207/30196

摘要： A computer-implemented method for generating a registered image (Breg) based on at least one first image of an object compliant with a source imaging modality and on at least one second image of the object compliant with a target imaging modality. The object may include a human body part, and the structures of interest may include stiff regions such as bones, cartilage, or tendons.

公开(公告)号：US12119090B1

公开(公告)日：2024-10-15

申请号：US18545399

申请日：2023-12-19

申请人： Recursion Pharmaceuticals, Inc.

发明人： Oren Zeev Kraus ,  Kian Runnels Kenyon-Dean ,  Mohammadsadegh Saberian ,  Maryam Fallah ,  Peter Foster McLean ,  Jessica Wai Yin Leung ,  Vasudev Sharma ,  Ayla Yasmin Khan ,  Jaichitra Balakrishnan ,  Safiye Celik ,  Dominique Beaini ,  Maciej Sypetkowski ,  Chi Cheng ,  Kristen Rose Morse ,  Maureen Katherine Makes ,  Benjamin John Mabey ,  Berton Allen Earnshaw

IPC分类号： G06T15/00 ,  G06T5/73 ,  G16B20/00 ,  G16B40/00 ,  G16B45/00

CPC分类号： G16B45/00 ,  G06T5/73 ,  G16B20/00 ,  G16B40/00 ,  G06T2207/10056 ,  G06T2207/20081 ,  G06T2207/20084

摘要： The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing generative machine learning models to generate embeddings from phenomic images (or other microscopy representations). For example, the disclosed systems can train a generative machine learning model (e.g., a masked autoencoder generative model) to generate predicted (or reconstructed) phenomic images from masked version of ground truth training phenomic images. In some cases, the disclosed systems utilize a momentum-tracking optimizer while reducing a loss of the generative machine learning model to enable efficient training on large scale training image batches. Furthermore, the disclosed systems can utilize Fourier transformation losses with multi-stage weighting to improve the accuracy of the generative machine learning model on the phenomic images during training. Indeed, the disclosed systems can utilize the trained generative machine learning model to generate phenomic embeddings from input phenomic images (for various phenomic comparisons).

公开(公告)号：US12118685B2

公开(公告)日：2024-10-15

申请号：US18378264

申请日：2023-10-10

申请人： Apple Inc.

发明人： Jean-Charles Bernard Marcel Bazin ,  Anselm Grundhoefer ,  Bart Trzynadlowski ,  Thomas J. Moore

IPC分类号： G06T19/00 ,  G06T7/70 ,  G06T15/00

CPC分类号： G06T19/006 ,  G06T7/70 ,  G06T15/00 ,  G06T2207/20081 ,  G06T2207/30244

摘要： Various implementations disclosed herein include devices, systems, and methods that provide XR in which virtual objects are positioned based on the accuracy of localizing an electronic device in a physical environment. In some implementations, the technique assesses the accuracy of localization (e.g., centimeter-level accuracy, room-level accuracy, and building-level accuracy) and dynamically adjusts a display strategy. In some implementations, the technique determines a condition causing inaccuracy (e.g., a semantic condition such as “too fast”, “too far”, “too dark”), and provides a notification (e.g., “too fast-slow down”, “too far-move closer”, “too dark-turn on a light”) at the electronic device based on the condition causing the inaccuracy in the localization.

公开(公告)号：US12118673B2

公开(公告)日：2024-10-15

申请号：US17864070

申请日：2022-07-13

申请人： Orqa Holding LTD

发明人： Srdjan Kovacevic ,  Ana Petrinec

IPC分类号： G06T19/00 ,  G06T15/00 ,  G06T17/00 ,  H04N23/698 ,  H04N23/90

CPC分类号： G06T19/003 ,  G06T15/005 ,  G06T17/00 ,  H04N23/698 ,  H04N23/90

摘要： A method for positioning of cameras on an object that enables accurate rendering of the scene around the object on a dome accurately in real time. The method involves providing a 3D model of the object having a surface, and selecting locations on the surface where the cameras are to be placed to provide a camera rig. The choice of locations is such that every camera has a field of view that overlaps with at least one other camera. The cameras are designated as Direct View Camera (DVC) or a Secondary View Camera (SVC). The method to render a virtual scene includes providing a projection rig that includes a plurality of projectors within a hollow half-sphere, wherein the hollow half-sphere includes an inner surface and an outer surface. Each of the plurality of projectors is designated as a Direct View Projector (DVP) or a Secondary View Projector (SVP).

公开(公告)号：US12118671B2

公开(公告)日：2024-10-15

申请号：US17627520

申请日：2020-07-20

申请人： Five AI Limited

发明人： Robert Chandler ,  Simon Walker ,  Benjamin Fuller ,  Thomas Westmacott

IPC分类号： G06T19/00 ,  G06N3/08 ,  G06N5/00 ,  G06T1/60 ,  G06T5/70 ,  G06T7/10 ,  G06T7/60 ,  G06T7/70 ,  G06T7/73 ,  G06T15/00 ,  G06T15/50 ,  G06T17/00 ,  G06T19/20 ,  G06V10/774 ,  G06V10/94 ,  G06V20/56 ,  G06V20/64

CPC分类号： G06T19/00 ,  G06N3/08 ,  G06N5/00 ,  G06T1/60 ,  G06T5/70 ,  G06T7/10 ,  G06T7/60 ,  G06T7/70 ,  G06T7/73 ,  G06T15/005 ,  G06T15/50 ,  G06T17/00 ,  G06T19/20 ,  G06V10/774 ,  G06V10/945 ,  G06V20/56 ,  G06V20/647 ,  G06T2200/08 ,  G06T2200/24 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/30252 ,  G06T2210/12 ,  G06T2219/004 ,  G06T2219/2004

摘要： A computer-implemented method of modelling a common structure component, the method comprising, in a modelling computer system: receiving a plurality of captured frames, each frame comprising a set of 3D structure points, in which at least a portion of a common structure component is captured; computing a first reference position within at least one first frame of the plurality of frames; selectively extracting first 3D structure points of the first frame based on the first reference position computed for the first frame; computing a second reference position within a second frame of the plurality of frames; selectively extracting second 3D structure points of the second frame based on the second reference position computed for the second frame; and aggregating the first 3D structure points and the second 3D structure points, thereby generating an aggregate 3D model of the common structure component based on the first and second reference positions.