-
公开(公告)号：US11688116B2
公开(公告)日：2023-06-27
申请号：US17411432
申请日：2021-08-25
CPC分类号： G06T13/40 , G06T7/251 , G06T17/205 , H04N5/04 , H04N23/90 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30201
摘要： An electronic device and method of preservation of geometry details in tracked meshes is provided. A set of three-dimensional (3D) scans and a sequence of tracked meshes of an object of interest are acquired. The sequence of tracked meshes comprises a set of tracked meshes which temporally corresponds to the set of 3D scans. Based on differences between the set of tracked meshes and the set of 3D scans, a set of displacement maps is generated. A plurality of vectors is computed, each of which includes surface tension values associated with mesh vertices of a corresponding tracked mesh. Based on the set of displacement maps and a corresponding set of vectors, a neural network is trained on a task of displacement map generation. The trained neural network model is applied on the plurality of vectors to generate displacement maps. Each tracked mesh is updated based on a corresponding displacement map.
-
公开(公告)号：US20230177871A1
公开(公告)日：2023-06-08
申请号：US17542916
申请日：2021-12-06
发明人： Ramin Eslami
CPC分类号： G06V40/165 , G06T7/60 , G06V10/82 , G06T7/73 , G06T2207/20084 , G06T2207/30201
摘要： An electronic device and method for face detection based on facial key-points is provided. The electronic device receives an image of an object of interest. The image may include a face of the object of interest. The electronic device detects a plurality of key-points associated with the face of the object of interest based on the received image and determines a first coordinate value in the received image based on the detected plurality of key-points. Thereafter, the electronic device determines a region in the received image that includes the face of the object of interest based on the determined first coordinate value and controls the display device to overlay a marker onto the determined region of the face. The marker indicates a location of the determined region in the image.
-
13.发明申请公开(公告)号：US20230103166A1
公开(公告)日：2023-03-30
申请号：US17488253
申请日：2021-09-28
IPC分类号： A63F13/525
摘要： A method predefines a virtual staircase connecting real platforms in an XR space by: accessing a previously generated spatial mapping mesh (SMM); compiling a record from the SMM of available surfaces; identifying available platforms provided by the physical elements and available open spaces therebetween; selecting a first platform at a first level and a second platform at a significantly lower level; selecting a staircase start location at a first edge of the first platform, partly based on predetermined criteria; stacking virtual blocks linearly to form a virtual staircase, with a first virtual block contacting and extending outwards from the first platform, and a last virtual block contacting the second platform at a staircase end location; and performing a collision analysis. If the staircase end location satisfies the predetermined criteria, and if no collisions are detected, the current virtual staircase is displayed in subsequent user interactions with the XR space.
-
公开(公告)号：US20230097571A1
公开(公告)日：2023-03-30
申请号：US17488250
申请日：2021-09-28
IPC分类号： A63F13/577 , A63F13/52 , A63F13/65
摘要： A method for quasi-random placement of a virtual item in an XR space includes: accessing a previously generated spatial mapping mesh (SMM) of the XR space; compiling a record from the SMM of open spaces between surfaces of physical elements in the XR space, with corresponding positions and dimensions; selecting from the open spaces: a spawn position for a virtual character, and a random set of other positions, filtering the random set to form a subset. The method then performs a collision analysis to assign a score to each position in the subset partly based on accessibility to that position for the virtual character beginning from the spawn position; and places the virtual item at a position in the subset having a score as high or higher than all other positions in the subset. The method is carried out before user interaction with any virtual element in the XR space.
-
公开(公告)号：US20230070940A1
公开(公告)日：2023-03-09
申请号：US17819285
申请日：2022-08-11
发明人： Qing Xia , Li-Hsiang Sun , Mohamed Abouelseoud , Liangxiao Xin
IPC分类号： H04W74/08
摘要： A preamble-based collision detection mechanism for use in wireless local area networks (WLANS), having one or more full-duplex (FD) stations. In addition, a new collision resolution estimation and scheduling mechanism is described for prioritized communication. These techniques can allow for more rapid collision detection and resolution, without the need of performing self-interference (SI) estimation. The techniques includes use of orthogonal preambles, in the time domain and/or frequency domain, into which FD stations embed priority information.
-
16.发明授权公开(公告)号：US11596866B1
公开(公告)日：2023-03-07
申请号：US17488249
申请日：2021-09-28
IPC分类号： A63F13/45 , A63F13/56 , A63F13/577
摘要： A method to generate an appropriate reaction, by an NPC in an XR game, to a significant event in the game includes: compiling a record from a previously generated SMM of surfaces in the XR space, categorizing the surfaces; after the game begins, tracking in real time physical surroundings of the NPC, allowing 3D positions of the NPC relative to nearby physical surfaces to be continuously determined; and events occurring in the game, allowing detection of any event deemed to be significant. For each detected event deemed significant, occurring at a corresponding event time, an appropriate action is determined for the NPC to carry out in response, partly based on whether the NPC is positioned close to a physical surface at the event time, and the NPC is directed to carry out the appropriate action.
-
公开(公告)号：US20230016302A1
公开(公告)日：2023-01-19
申请号：US17861033
申请日：2022-07-08
IPC分类号： G06T9/00
摘要： Methods, systems and device for efficiently compressing task-oriented dynamic meshes using occupancy networks are described herein. A single trained occupancy network model is able to reconstruct a mesh video using a few additional points per input mesh frame. To optimize the compression of the model and points, the estimated rate to compress the occupancy network is able to be included in the loss function. This minimizes the number of bits to encode the model, while it tries to reproduce the meshes as well as possible. An adaptive subsampling per input mesh is added to optimize the mesh reconstruction and the N-point point clouds compression. To optimize the model to perform a particular task, a metric is added to the cost function that takes this task into account.
-
公开(公告)号：US20230013421A1
公开(公告)日：2023-01-19
申请号：US17828326
申请日：2022-05-31
IPC分类号： H04N19/597 , G06V10/764 , G06V10/82 , G06V20/64 , H04N19/13 , H04N19/167 , H04N19/29 , H04N19/436 , H04N19/132
摘要： Occupancy networks enable efficient and flexible point cloud compression. In addition to the voxel-based representation, occupancy networks are able to handle points, meshes, or projected images of 3D objects, making them very flexible in terms of input signal representation. The probability of occupancy of positions is estimated using occupancy networks instead of sparse convolutional neural networks. A compression implementation using occupancy network enables scalability with infinite reconstruction resolution.
-
公开(公告)号：US20220398396A1
公开(公告)日：2022-12-15
申请号：US17344730
申请日：2021-06-10
发明人： Wanxin Xu , Ko-Kai Albert Huang
摘要： Implementations generally recognize clinical activity using multiple cameras. In some implementations, a method includes obtaining a plurality of videos of a plurality of objects in an environment. The method further includes determining one or more key points for each object of the plurality of objects. The method further includes recognizing activity information based on the one or more key points. The method further includes computing workflow information based on the activity information.
-
公开(公告)号：US11516848B2
公开(公告)日：2022-11-29
申请号：US17233305
申请日：2021-04-16
发明人： Liangxiao Xin , Mohamed Abouelseoud
摘要： Multiple solutions for a non-STR (simultaneous transmit and receive) MLD (Multi-Link Device) contending and accessing the channel on a second link, during the detection time of the packet transmission on a first link. The solutions involve performing select backoff count-down procedures, channel accessing, and backoff initialization/re-initialization that the non-STR MLD should perform on the second link during its detection time on the first link.
-
-
-
-
-
-
-
-
-
搜索结果
204 条记录 (耗时 0.032 秒)
