公开(公告)号：US20240362851A1

公开(公告)日：2024-10-31

申请号：US18769000

申请日：2024-07-10

Applicant: NVIDIA Corporation

Inventor： Gregory MUTHLER ,  John BURGESS

IPC: G06T15/06 ,  G06F9/50 ,  G06T15/08 ,  G06T17/00 ,  G06T17/10

CPC classification number: G06T15/06 ,  G06F9/5027 ,  G06T15/08 ,  G06T17/005 ,  G06T17/10 ,  G06T2210/12

Abstract: A bounding volume is used to approximate the space an object occupies. If a more precise understanding beyond an approximation is required, the object itself is then inspected to determine what space it occupies. Often, a simple volume (such as an axis-aligned box) is used as bounding volume to approximate the space occupied by an object. But objects can be arbitrary, complicated shapes. So a simple volume often does not fit the object very well. That causes a lot of space that is not occupied by the object to be included in the approximation of the space being occupied by the object. Hardware-based techniques are disclosed herein, for example, for efficiently using multiple bounding volumes (such as axis-aligned bounding boxes) to represent, in effect, an arbitrarily shaped bounding volume to better fit the object, and for using such arbitrary bounding volumes to improve performance in applications such as ray tracing.

公开(公告)号：US12131509B2

公开(公告)日：2024-10-29

申请号：US17690671

申请日：2022-03-09

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Chung Dean Han ,  Pongsak Lasang ,  Pradit Mittrapiyanuruk ,  Keng Liang Loi ,  Noritaka Iguchi ,  Toshiyasu Sugio

IPC: H04N13/161 ,  G06T9/00 ,  G06T9/40 ,  H04N19/17 ,  G06T17/00 ,  H04N7/24 ,  H04N19/96 ,  H04N21/236 ,  H04N21/81

CPC classification number: G06T9/40 ,  G06T9/00 ,  H04N19/17 ,  G06T17/00 ,  G06T17/005 ,  G06T2200/04 ,  G06T2207/10028 ,  G06T2207/20021 ,  H04N2007/243 ,  H04N13/161 ,  H04N19/96 ,  H04N21/23614 ,  H04N21/8146 ,  H04N21/816

Abstract: A three-dimensional data encoding method includes: encoding three-dimensional points each located in any one of a plurality of regions, on a per region basis, to generate encoded three-dimensional points; generating connectivity information generated based on a relationship between a first region among the plurality of regions and second regions aside from the first region among the plurality of regions, the connectivity information including (i) tile information indicating values each uniquely assigned to a different one of the plurality of regions and (ii) relation information indicating that the first region and one of the second regions are related; and generating a bitstream including the connectivity information generated and the encoded three-dimensional points.

公开(公告)号：US20240346757A1

公开(公告)日：2024-10-17

申请号：US18753430

申请日：2024-06-25

Applicant: Willow Garage, LLC

Inventor： Eitan MARDER-EPPSTEIN ,  Stuart GLASER ,  Wim MEEUSSEN

IPC: G06T17/00 ,  G06F3/04815 ,  G06F3/0484 ,  G06F16/22 ,  G06F16/51 ,  G06T15/20 ,  G06T17/05 ,  H04L67/1097

CPC classification number: G06T17/005 ,  G06F3/04815 ,  G06F3/0484 ,  G06F16/2246 ,  G06F16/51 ,  G06T15/20 ,  G06T17/05 ,  H04L67/1097 ,  G06T2200/24 ,  G06T2210/36 ,  G06T2210/56

Abstract: A system comprises a storage system comprising data representing a point cloud comprising a very large number of associated points; a controller operatively coupled to the storage cluster and configured to organize the data into an octree hierarchy of data sectors, each of which is representative of one or more of the points at a given octree mesh resolution; and a user interface through which a user may select a viewing perspective origin and vector, which may be utilized to command the controller to assemble an image based at least in part upon the selected origin and vector, the image comprising a plurality of data sectors pulled from the octree hierarchy, the plurality of data sectors being assembled such that sectors representative of points closer to the selected viewing origin have a higher octree mesh resolution than that of sectors representative of points farther away from the selected viewing origin.

公开(公告)号：US12118664B2

公开(公告)日：2024-10-15

申请号：US17485043

申请日：2021-09-24

Applicant: L3VEL, LLC

Inventor： Kevin Ross ,  Muhammad Ahsan Naim

IPC: G06T17/05 ,  G06T17/00 ,  G06V10/25 ,  G06V10/26 ,  H04W16/20

CPC classification number: G06T17/05 ,  G06T17/005 ,  G06V10/25 ,  G06V10/267 ,  H04W16/20

Abstract: Disclosed herein are systems and methods that relate to wireless communication mesh network design and operation. In one aspect, the disclosed process may involve (1) obtaining potential-customer information related to a set of potential customers for a service to be provided through a wireless communication mesh network in an AOI, where the potential-customer information comprises both (i) information related to potential customers that are identified during a pre-marketing phase and (ii) information related to potential customers that are identified during a door-to-door marketing phase, and where the set of potential customers have a corresponding set of customer locations in the AOI, (2) evaluating the obtained potential-customer information and thereby identifying a subset of customer locations at which to deploy the wireless communication mesh network, and (3) generating and outputting information that facilitates deployment of the wireless communication mesh network at the identified subset of customer locations in the AOI.

公开(公告)号：US12112471B2

公开(公告)日：2024-10-08

申请号：US17456145

申请日：2021-11-22

Applicant: GE Precision Healthcare LLC

Inventor： Mario Viti ,  Faycal El Hanchi El Amrani ,  Nicolas Gogin ,  Celine Pruvot

IPC: G06T7/11 ,  A61B5/00 ,  G06N3/045 ,  G06N3/08 ,  G06T7/00 ,  G06T17/00

CPC classification number: G06T7/0012 ,  A61B5/7264 ,  G06N3/045 ,  G06N3/08 ,  G06T7/11 ,  G06T17/005 ,  G06T2207/10081 ,  G06T2207/30048 ,  G06T2207/30096 ,  G06T2207/30101

Abstract: Methods and systems are provided for detecting coronary lesions in 3D cardiac computed tomography and angiography (CCTA) images using deep neural networks. In an exemplary embodiment, a method for detecting coronary lesions in 3D CCTA images comprises, acquiring a 3D CCTA image of a coronary tree, mapping the 3D CCTA image to a multi-label segmentation map with a trained deep neural network, generating a plurality of 1D parametric curves for a branch of the coronary tree using the multi-label segmentation map, determining a location of a lesion in the branch of the coronary tree using the plurality of 1D parametric curves, and determining a severity score for the lesion based on the plurality of 1D parametric curves.

公开(公告)号：US20240331661A1

公开(公告)日：2024-10-03

申请号：US18616064

申请日：2024-03-25

Applicant: Apple Inc.

Inventor： Yashas Rai Kurlethimar ,  Nathaniel C. Begeman ,  Seyedkoosha Mirhosseini

IPC: G09G5/391 ,  G02B27/00 ,  G02B27/01 ,  G06F3/01 ,  G06T9/00 ,  G06T17/00 ,  H04N19/625 ,  H04N19/96

CPC classification number: G09G5/391 ,  G02B27/0093 ,  G02B27/0172 ,  G06F3/012 ,  G06T9/007 ,  G06T17/005 ,  H04N19/625 ,  H04N19/96 ,  G06T2207/20052 ,  G09G2340/0407

Abstract: Prior to rendering a current frame, a device obtains a previously rendered frame. The device determines that a first portion of the previously rendered frame is associated with a particular type of content. The device renders a first portion of the current frame that corresponds to the first portion of the previously rendered frame with a first rendering characteristic while rendering a second portion of the current frame with a second rendering characteristic that is different from the first rendering characteristic.

公开(公告)号：US20240320914A1

公开(公告)日：2024-09-26

申请号：US18733648

申请日：2024-06-04

Applicant: Willow Garage, LLC

Inventor： Stuart GLASER ,  Wim MEEUSSEN ,  Eitan MARDER-EPPSTEIN

IPC: G06T17/00 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04845 ,  G06F3/04847 ,  G06F16/22 ,  G06F16/26 ,  G06F16/28 ,  G06T15/20 ,  G06T17/05 ,  G06T17/20

CPC classification number: G06T17/005 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04845 ,  G06F3/04847 ,  G06F16/2246 ,  G06F16/26 ,  G06F16/282 ,  G06F16/287 ,  G06T17/05 ,  G06T17/20 ,  G06T15/20 ,  G06T2207/10028 ,  G06T2210/56

Abstract: One embodiment is directed to a system for presenting views of a very large point data set, comprising: a storage system comprising data representing a point cloud comprising a very large number of associated points; a controller operatively coupled to the storage cluster and configured to automatically and deterministically organize the point data into an octree hierarchy of data sectors, each of which is representative of one or more of the points at a given octree mesh resolution; and a user interface through which a user may select a viewing perspective origin and vector, which may be utilized to command the controller to assemble an image based at least in part upon the selected origin and vector, the image comprising a plurality of data sectors pulled from the octree hierarchy.

公开(公告)号：US12085392B2

公开(公告)日：2024-09-10

申请号：US18102613

申请日：2023-01-27

Applicant: Movidius Ltd.

Inventor： David Macdara Moloney ,  Xiaofan Xu

IPC: G06T15/08 ,  G01C21/20 ,  G01C21/30 ,  G05D1/00 ,  G05D1/246 ,  G05D1/617 ,  G06F9/30 ,  G06F17/16 ,  G06N3/04 ,  G06N3/045 ,  G06T1/20 ,  G06T15/06 ,  G06T17/00 ,  G06T17/05 ,  G06T19/00 ,  G06V20/13 ,  G06V20/17 ,  G06V20/64 ,  G06N3/048

CPC classification number: G01C21/20 ,  G01C21/30 ,  G05D1/0214 ,  G05D1/0274 ,  G05D1/246 ,  G05D1/617 ,  G06F9/30029 ,  G06F17/16 ,  G06N3/04 ,  G06N3/045 ,  G06T1/20 ,  G06T15/06 ,  G06T15/08 ,  G06T17/005 ,  G06T17/05 ,  G06T19/00 ,  G06T19/006 ,  G06V20/13 ,  G06V20/17 ,  G06V20/64 ,  G06N3/048 ,  G06T2200/04 ,  G06T2200/28 ,  G06T2210/08 ,  G06T2210/36 ,  G06T2219/004

Abstract: An output of a first one of a plurality of layers within a neural network is identified. A bitmap is determined from the output, the bitmap including a binary matrix. A particular subset of operations for a second one of the plurality of layers is determined to be skipped based on the bitmap. Operations are performed for the second layer other than the particular subset of operations, while the particular subset of operations are skipped.

公开(公告)号：US20240296629A1

公开(公告)日：2024-09-05

申请号：US18112445

申请日：2023-02-21

Applicant: Tencent America LLC

Inventor： Xifeng GAO ,  Zhen CHEN ,  Zherong PAN ,  Kui WU

IPC: G06T17/20 ,  G06T17/00 ,  G06T19/20

CPC classification number: G06T17/205 ,  G06T17/005 ,  G06T19/20 ,  G06T2219/2004

Abstract: According to an aspect of the disclosure, a method of generating a low-poly mesh for a three-dimensional (3D) model is provided. In the method, an edge-collapse operation is performed on each of a plurality of edges of an input mesh to generate a simplified mesh in which a number of faces of the input mesh is reduced by the edge-collapse operation. A position of at least one vertex of the simplified mesh is updated to generate an updated mesh in which a distance between the simplified mesh and the input mesh is reduced. The low-poly mesh is generated based on an aligned mesh in which positions of vertices of the updated mesh are optimized by minimizing a shape difference between the simplified mesh and the updated mesh.

公开(公告)号：US20240280376A1

公开(公告)日：2024-08-22

申请号：US18171848

申请日：2023-02-21

Applicant: GM Global Technology Operations LLC

Inventor： Gui Chen ,  Bo Yu ,  Brent Navin Roger Bacchus ,  Shu Chen ,  Joon Hwang ,  Michael Alan Losh

IPC: G01C21/00 ,  G01C21/32 ,  G06T7/38 ,  G06T17/00 ,  G06T17/05

CPC classification number: G01C21/3881 ,  G01C21/32 ,  G01C21/3815 ,  G06T7/38 ,  G06T17/005 ,  G06T17/05 ,  G06T2207/10028

Abstract: A method for quantifying map errors includes receiving first map data and second map data. The method includes receiving a road topographic map. The method further includes dividing the road into road segments. The method further includes creating a plurality of bounding boxes for each of the plurality of road segments. The method includes creating a first map tile and a second map tile by filtering out the bounding boxes. The method includes executing point cloud registration to align the plurality of first data points in the first map tile with the plurality of second data points in the second map tile to determine a plurality of absolute offsets between the plurality of first data points and the plurality of second data points. The method includes determining a relative map error between the first map and the second map based on the absolute offsets.