公开(公告)号：US11880935B2

公开(公告)日：2024-01-23

申请号：US17951405

申请日：2022-09-23

申请人： SHANGHAITECH UNIVERSITY

发明人： Minye Wu ,  Jingyi Yu

IPC分类号： G06T17/00 ,  G06V10/82 ,  G06F18/214 ,  G06F18/213 ,  G06T15/04 ,  G06T15/20 ,  G06T17/20 ,  G06V20/64 ,  G06T7/593 ,  H04N13/207

CPC分类号： G06T17/00 ,  G06F18/213 ,  G06F18/214 ,  G06T7/593 ,  G06T15/04 ,  G06T15/205 ,  G06T17/20 ,  G06V10/82 ,  G06V20/653 ,  H04N13/207 ,  G06T2200/08 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2210/56

摘要： An image-based method of modeling and rendering a three-dimensional model of an object is provided. The method comprises: obtaining a three-dimensional point cloud at each frame of a synchronized, multi-view video of an object, wherein the video comprises a plurality of frames; extracting a feature descriptor for each point in the point cloud for the plurality of frames without storing the feature descriptor for each frame; producing a two-dimensional feature map for a target camera; and using an anti-aliased convolutional neural network to decode the feature map into an image and a foreground mask.

公开(公告)号：US11842517B2

公开(公告)日：2023-12-12

申请号：US16843281

申请日：2020-04-08

申请人： Ultrahaptics IP Ltd

发明人： Samuel John Llewellyn Lyons

IPC分类号： G06K9/62 ,  G06V20/64 ,  G06T7/73 ,  G06N3/084 ,  G06V40/10 ,  G06F18/21 ,  G06F18/2111 ,  G06F18/214 ,  G06N3/045 ,  G06V10/764 ,  G06V10/82 ,  G06V10/426 ,  G06V40/20 ,  G06N3/126

CPC分类号： G06T7/75 ,  G06F18/217 ,  G06F18/2111 ,  G06F18/2155 ,  G06N3/045 ,  G06N3/084 ,  G06N3/126 ,  G06V10/426 ,  G06V10/764 ,  G06V10/82 ,  G06V20/653 ,  G06V40/11 ,  G06V40/28 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Described is a solution for an unlabeled target domain dataset challenge using a domain adaptation technique to train a neural network using an iterative 3D model fitting algorithm to generate refined target domain labels. The neural network supports the convergence of the 3D model fitting algorithm and the 3D model fitting algorithm provides refined labels that are used for training of the neural network. During real-time inference, only the trained neural network is required. A convolutional neural network (CNN) is trained using labeled synthetic frames (source domain) with unlabeled real depth frames (target domain). The CNN initializes an offline iterative 3D model fitting algorithm capable of accurately labeling the hand pose in real depth frames. The labeled real depth frames are used to continue training the CNN thereby improving accuracy beyond that achievable by using only unlabeled real depth frames for domain adaptation.

公开(公告)号：US20230334807A1

公开(公告)日：2023-10-19

申请号：US18132071

申请日：2023-04-07

申请人： NEC Corporation

发明人： Kiri Inayoshi ,  Takashi Nonaka ,  Kentaro Nishida

IPC分类号： G06T19/20 ,  G06V20/64 ,  G06T15/04 ,  G06V10/778

CPC分类号： G06T19/20 ,  G06V20/653 ,  G06T15/04 ,  G06V10/7788 ,  G06T2219/2021 ,  G06T2219/2016 ,  G06T2200/24 ,  G06T2210/04

摘要： An information processing device includes at least one processor configured to execute: an obtaining process of obtaining three-dimensionally scanned data; an identifying process of identifying a three-dimensional model corresponding to the subject; and an output process of outputting the three-dimensional model, the at least one processor being further configured to execute, in the identifying process, an object detecting process of performing a process of object detection to identify an object; and a searching process of searching, in three-dimensional model candidates, for the three-dimensional model corresponding to the object.

公开(公告)号：US11783543B2

公开(公告)日：2023-10-10

申请号：US17202578

申请日：2021-03-16

申请人： Hover Inc.

发明人： Manish Upendran ,  Adam J. Altman

IPC分类号： G06T19/00 ,  G06T17/05 ,  G06T15/20 ,  G06V20/10 ,  G06V20/64 ,  G06T15/04

CPC分类号： G06T19/00 ,  G06T15/04 ,  G06T15/20 ,  G06T17/05 ,  G06V20/176 ,  G06V20/653 ,  G06T2200/08 ,  G06T2210/04 ,  G06T2210/56

摘要： Visualizing three dimensional content is complicated by display platforms capable of more degrees of freedom to display the content than interface tools have to navigate that content. Disclosed are methods and systems for displaying select portions of the content and generating virtual camera positions with associated look angles for the select portions, such as planar geometries of a three dimensional building, thereby constraining the degrees of freedom for improved navigation through views of the content. Look angles can be associated with axes of the content and fields of view.

公开(公告)号：US20230306760A1

公开(公告)日：2023-09-28

申请号：US17901471

申请日：2022-09-01

申请人： FUJIFILM Business Innovation Corp.

发明人： Ryosuke HIGASHIKATA ,  Tomonari TAKAHASHI ,  Atsushi OGIHARA ,  Yasuyuki TANAKA ,  Yumi SEKIGUCHI ,  Shunji SAKAI ,  Yasushi UEMURA

IPC分类号： G06V20/64 ,  G06T15/20 ,  G06T7/00

CPC分类号： G06V20/653 ,  G06T15/20 ,  G06T7/0004

摘要： An information processing apparatus includes a processor configured to: determine a relationship between first product manufacturing information and second product manufacturing information included in three-dimensional model data; and generate, on a basis of the determined relationship, information indicating the relationship between the first product manufacturing information and the second product manufacturing information.

公开(公告)号：US11756211B2

公开(公告)日：2023-09-12

申请号：US17411386

申请日：2021-08-25

申请人： 7-ELEVEN, INC.

发明人： Sailesh Bharathwaaj Krishnamurthy ,  Shahmeer Ali Mirza

IPC分类号： G06T7/246 ,  G06T7/292 ,  G06T7/223 ,  G06T7/215 ,  G06V20/52 ,  G06V10/25 ,  G06V10/44 ,  G06V10/147 ,  G06V20/64 ,  G06V10/24

CPC分类号： G06T7/246 ,  G06T7/215 ,  G06T7/223 ,  G06T7/292 ,  G06V10/147 ,  G06V10/25 ,  G06V10/457 ,  G06V20/52 ,  G06V20/653 ,  G06T2207/10021 ,  G06T2207/30232 ,  G06V10/245

摘要： An object tracking system includes a first sensor, a second sensor, and a tracking system. The first sensor is configured to capture a first frame of a global plane for at least a first portion of a space. The second sensor is configured to capture a second frame of at least a second portion of the space. The tracking system is configured to determine the object is within an overlap region with the second sensor based on a first pixel location. The tracking system is further configured to determine a first coordinate in the global plane for the object, to determine a second pixel location in the second frame for the object based on the first coordinate, and to store the second pixel location with an object identifier a tracking list associated with the second sensor.

公开(公告)号：US11751660B2

公开(公告)日：2023-09-12

申请号：US16991428

申请日：2020-08-12

申请人： Zhejiang Xunshi Technology Co., Ltd

发明人： Jing Zhang ,  Biqing Lu ,  Yong Chen ,  Tiantian Wang ,  Weigang Jin ,  Ming Chen ,  Haiyan Feng

IPC分类号： A45D31/00 ,  B33Y50/00 ,  B33Y80/00 ,  G06T17/00 ,  G06V20/64 ,  A45D29/00

CPC分类号： A45D31/00 ,  B33Y50/00 ,  B33Y80/00 ,  G06T17/00 ,  G06V20/653 ,  A45D2029/005 ,  G06T2207/30196 ,  G06T2219/2021

摘要： A production method of a digitized artificial nail for a nail of a user includes the steps of: (a) scanning the nail of the user to construct an irregular digitized user nail model; (b) data sampling to convert the irregular digitized user nail model into a regular digitized artificial nail model which is a regular three dimensional grid surface, and topology deformation of the regular three dimensional grid surface to form a digitized artificial nail model; (c) matching an artificial nail shape selected by the user with the digitized artificial nail model to obtain a desired artificial nail model; (d) customizing the digitized artificial nail model; and (e) three dimensional printing a digitized artificial nail in response to the digitized artificial nail model.

公开(公告)号：US20230260212A1

公开(公告)日：2023-08-17

申请号：US18306775

申请日：2023-04-25

申请人： Hover Inc.

发明人： Derek Halliday ,  Antonio Carlos Marques da Silva Junior ,  Roberto Klein ,  Adam J. Altman

IPC分类号： G06T17/00 ,  G06T19/20 ,  G06T17/05 ,  G06T15/04 ,  G06V20/10 ,  G06V20/64 ,  G06F30/13 ,  G06F30/23 ,  G06F3/14 ,  G06T15/20 ,  G06T19/00

CPC分类号： G06T17/00 ,  G06T19/20 ,  G06T17/05 ,  G06T15/04 ,  G06V20/176 ,  G06V20/653 ,  G06F30/13 ,  G06F30/23 ,  G06F3/14 ,  G06T15/20 ,  G06T19/003 ,  G06T2200/08 ,  G06T2210/04 ,  G06T2219/004 ,  G06T2219/2016 ,  G06T2210/56 ,  G06T2200/24 ,  G06T2207/10028 ,  G06T2219/2008

摘要： A system and method is provided for constructing a labeled and dimensioned multidimensional (e.g., 3D) building model from building object imagery (e.g., ground-level imagery). The method begins by retrieve building object imagery, the building object imagery collected based on directed capture with a mobile device. The method continues by constructing a scaled multi-dimensional building model, the scale based on sizing of at least one selected architectural feature. The method continues by identifying architectural elements within facades of the multi-dimensional building model. The method continues by determining dimensions of at least one of the architectural elements, the dimensions based on the scale. The method continues by determining dimensions (e.g., area) of at least one of the architectural elements. The method continues by labeling each identified architectural element with at least an identifier and by labeling at least one of the architectural elements with the determined dimensions.

公开(公告)号：US11727575B2

公开(公告)日：2023-08-15

申请号：US17487418

申请日：2021-09-28

申请人： COVAR APPLIED TECHNOLOGIES, INC.

发明人： Peter A. Torrione ,  Mark Hibbard

IPC分类号： G06K9/00 ,  G06T7/11 ,  G06T7/70 ,  G06V20/64 ,  G06F18/22 ,  G06V10/764 ,  G06V10/82 ,  G06V10/26 ,  G06V20/52 ,  G06N3/08

CPC分类号： G06T7/11 ,  G06F18/22 ,  G06T7/70 ,  G06V10/26 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V20/647 ,  G06V20/653 ,  G06N3/08 ,  G06T2207/20084

摘要： A system and method for recognizing objects in an image is described. The system can receive an image from a sensor and detect one or more objects in the image. The system can further detect one or more components of each detected object. Subsequently, the system can create a segmentation map based on the components detected for each detected object and determine whether the segmentation map matches a plurality of 3-D models (or projections thereof). Additionally, the system can display a notification through a user interface indicating whether the segmentation map matches at least one of the plurality of 3-D models.

公开(公告)号：US11709049B2

公开(公告)日：2023-07-25

申请号：US16977868

申请日：2019-02-28

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Shigehiro Matsuda ,  Takashi Goto ,  Ryuji Honda ,  Yoshiyuki Kajihara

IPC分类号： G01B11/24 ,  G06T7/62 ,  G06T7/00 ,  G06V20/64

CPC分类号： G01B11/24 ,  G06T7/0002 ,  G06T7/62 ,  G06V20/653 ,  G06T2207/30184

摘要： Even when a missing portion occurs in a solid data set on a columnar structure, an estimator for a deflection value and an accuracy of the deflection value are correctly estimated according to an extent of the missing portion and the like. A measurement accuracy estimation unit (15) is included that: calculates a deflection of a columnar structure and an extent of a missing portion, from a solid data set on the columnar structure; calculates an accuracy assessment indicator for the deflection that is acquirable when a plurality of missing portion patterns occur on a virtual basis, based on a plurality of solid data sets in each of which the calculated extent of the missing portion is smaller than a preset threshold value, the accuracy assessment indicator being calculated for each missing portion pattern; and calculates an accuracy of the deflection calculated from the solid data set, based on the calculated accuracy assessment indicator for each missing portion pattern, and based on the calculated extent of the missing portion in the solid data set.