-
公开(公告)号:US12131422B2
公开(公告)日:2024-10-29
申请号:US17963471
申请日:2022-10-11
发明人: Bingbing Zhuang , Samuel Schulter , Yi-Hsuan Tsai , Buyu Liu , Nanbo Li
CPC分类号: G06T15/20 , G06T15/00 , G06T17/00 , G06V10/774 , G06V10/82 , G06V20/41 , G06T2200/08 , G06T2210/56
摘要: A method for achieving high-fidelity novel view synthesis and 3D reconstruction for large-scale scenes is presented. The method includes obtaining images from a video stream received from a plurality of video image capturing devices, grouping the images into different image clusters representing a large-scale 3D scene, training a neural radiance field (NeRF) and an uncertainty multilayer perceptron (MLP) for each of the image clusters to generate a plurality of NeRFs and a plurality of uncertainty MLPs for the large-scale 3D scene, applying a rendering loss and an entropy loss to the plurality of NeRFs, performing uncertainty-based fusion to the plurality of NeRFs to define a fused NeRF, and jointly fine-tuning the plurality of NeRFs and the plurality of uncertainty MLPs, and during inference, applying the fused NeRF for novel view synthesis of the large-scale 3D scene.
-
公开(公告)号:US12131416B2
公开(公告)日:2024-10-29
申请号:US17556367
申请日:2021-12-20
发明人: Stephen Anthony Lombardi , Jason Saragih , Tomas Simon Kreuz , Shunsuke Saito , Michael Zollhoefer , Amit Raj , James Henry Hays
CPC分类号: G06T13/40 , G06T7/73 , G06T7/97 , G06T2207/30201
摘要: A method of forming a pixel-aligned volumetric avatar includes receiving multiple two-dimensional images having at least two or more fields of view of a subject. The method also includes extracting multiple image features from the two-dimensional images using a set of learnable weights, projecting the image features along a direction between a three-dimensional model of the subject and a selected observation point for a viewer, and providing, to the viewer, an image of the three-dimensional model of the subject. A system and a non-transitory, computer readable medium storing instructions to perform the above method, are also provided.
-
公开(公告)号:US12131413B2
公开(公告)日:2024-10-29
申请号:US17920491
申请日:2021-04-22
CPC分类号: G06T11/206 , A61B5/0006 , A61B5/339 , A61B5/384 , A61B5/4812 , A61B5/7435 , A61B5/748 , G16H20/30 , G16H40/67 , G16H50/50 , G06T2200/24 , G06T2210/41
摘要: An apparatus comprises at least one processing device comprising a processor coupled to a memory. The at least one processing device is configured to select physiologic data to be visualized, the selected physiologic data comprising a given set of one or more physiologic parameters collected from a given set of one or more subjects over a given period of time. The at least one processing device is also configured to determine a plot type for visualization of the selected physiologic data, the plot type being determined based at least in part on a repetitiveness of the selected physiologic data over a plurality of time segments in the given period of time. The at least one processing device is further configured to generate a visualization of the selected physiologic data utilizing the determined plot type, and to output the generated visualization of the selected physiologic data via an interactive graphical user interface.
-
公开(公告)号:US12131410B2
公开(公告)日:2024-10-29
申请号:US17293958
申请日:2019-11-15
CPC分类号: G06T11/008 , A61B6/037 , G06T11/006 , G06T2211/424
摘要: A non-transitory computer-readable medium stores instructions readable and executable by a workstation (18) including at least one electronic processor (20) to perform an imaging method (100). The method includes: receiving imaging data on a frame by frame basis for frames along an axial direction with neighboring frames overlapping along the axial direction wherein the frames include at least a volume (k) and a succeeding volume (k+1) at least partially overlapping the volume (k) along the axial direction; and generating an image of the volume (k) using an iterative image reconstruction process in which an iteration of the iterative image reconstruction process includes: computing a local penalty function for suppressing noise over the volume (k) including reducing the value of the local penalty function in an overlap region; generating an update image of the volume (k) using imaging data from the volume (k) and further using the local penalty function.
-
公开(公告)号:US12131363B2
公开(公告)日:2024-10-29
申请号:US18232134
申请日:2023-08-09
申请人: Shutterfly, LLC
发明人: Omer Moshe Moussaffi
CPC分类号: G06Q30/0621 , G06F16/51 , G06F18/22 , G06Q30/0643 , G06T11/60 , G06V10/761 , G06T2200/24 , G06V40/161 , G06V40/172
摘要: A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.
-
96.
公开(公告)号:US12131360B2
公开(公告)日:2024-10-29
申请号:US17319895
申请日:2021-05-13
申请人: CARVANA, LLC
IPC分类号: G06Q30/0601 , G03B37/02 , G06Q40/03 , G06T11/60 , G06T13/00 , G06T13/80 , G06T19/00 , H04N5/222 , H04N7/18 , H04N23/56 , H04N23/661 , H04N23/698 , H04N23/90 , G03B17/56 , G06F3/0482
CPC分类号: G06Q30/0609 , G03B37/02 , G06Q30/0641 , G06Q30/0643 , G06Q40/03 , G06T11/60 , G06T13/00 , G06T13/80 , G06T19/006 , H04N5/2224 , H04N7/181 , H04N23/56 , H04N23/661 , H04N23/698 , H04N23/90 , G03B17/561 , G06F3/0482 , G06F2203/04806 , G06T2200/24
摘要: Systems, methods, and devices of the various embodiments enable online transactions related to buying/selling an item, such as a vehicle. In an embodiment, one or more installment agreements relating to a user and one or more items may be generated in response to one or more received inputs. In an embodiment, a deal table comprising the one or more installment agreements may be generated, and the deal table may be transmitted to a user device for presentation via the user interface.
-
公开(公告)号:US12131355B2
公开(公告)日:2024-10-29
申请号:US16907946
申请日:2020-06-22
发明人: Christine Soule , Charles H. Cella , Richard Spitz
IPC分类号: G06Q30/02 , G01C21/20 , G06F3/01 , G06F3/0482 , G06F16/435 , G06F16/438 , G06F16/587 , G06F16/953 , G06F16/9535 , G06F16/954 , G06N20/00 , G06Q10/047 , G06Q20/20 , G06Q30/0201 , G06Q30/0203 , G06Q30/0207 , G06Q30/0214 , G06Q30/0217 , G06Q30/0251 , G06Q30/0279 , G06Q30/0282 , G06Q50/00 , G06T5/00 , G06T11/00 , G06T11/60 , G06V20/20 , G06V20/52 , G06V40/16 , H04L9/40 , H04L67/12 , H04L67/50 , H04N7/15 , H04N21/2187 , H04W4/021 , H04W4/024 , H04W4/029 , H04W4/10 , H04W4/12 , H04W4/33 , H04W4/80 , H04W12/06 , H04W12/08 , H04W12/084 , G06K7/14 , G06Q50/26 , H04W12/64
CPC分类号: G06Q30/0279 , G01C21/206 , G06F3/013 , G06F3/0482 , G06F16/435 , G06F16/438 , G06F16/587 , G06F16/953 , G06F16/9535 , G06F16/954 , G06N20/00 , G06Q10/047 , G06Q20/20 , G06Q30/0201 , G06Q30/0203 , G06Q30/0207 , G06Q30/0214 , G06Q30/0217 , G06Q30/0224 , G06Q30/0236 , G06Q30/0261 , G06Q30/0267 , G06Q30/0271 , G06Q30/0281 , G06Q30/0282 , G06Q50/01 , G06T5/005 , G06T11/00 , G06T11/60 , G06V20/20 , G06V20/52 , G06V40/16 , G06V40/176 , H04L63/0861 , H04L67/12 , H04L67/535 , H04N7/15 , H04N21/2187 , H04W4/021 , H04W4/024 , H04W4/029 , H04W4/10 , H04W4/12 , H04W4/33 , H04W4/80 , H04W12/068 , H04W12/08 , H04W12/084 , G06K7/1417 , G06Q50/26 , G06V2201/10 , H04W12/64
摘要: An information technology platform for personalizing an experience of a visitor at a non-profit venue comprising: a network; a server in communication with the network; a mobile computing device to be carried by a visitor to a non-profit venue, wherein the platform determines personalized information about the visitor and a recommendation engine outputs a suggestion for a personalized experience to the visitor to encourage philanthropic activity related to an ongoing philanthropic campaign; and a machine learning system for learning on a training set of photographic data or video data, the learning to train the machine learning system to predict a sentiment towards the ongoing philanthropic campaign of the visitor based, at least in part, on photographic images or video images that are taken by the visitor, that are shared to the visitor, that are shared by the visitor or that include the visitor as a subject.
-
公开(公告)号:US12131300B1
公开(公告)日:2024-10-29
申请号:US17071751
申请日:2020-10-15
发明人: Bharat Prasad , Minya Liang , Reynaldo Medina, III
IPC分类号: G06Q20/04 , G06Q20/32 , G06V30/146 , G06V30/40 , H04N5/44 , H04N23/60 , H04N23/63 , G06T7/73
CPC分类号: G06Q20/042 , G06Q20/3223 , G06V30/146 , G06V30/1465 , G06V30/40 , H04N5/44 , H04N23/63 , H04N23/64 , G06T7/73
摘要: An alignment guide may be provided in the field of view of a camera associated with a mobile device used to capture an image of a check. When the image of the check is within the alignment guide in the field of view, an image may be taken by the camera and provided from the mobile device to a financial institution. The alignment guide may be adjustable at the mobile device. The image capture may be performed automatically by the camera or the mobile device as soon as the image of the check is determined to be within the alignment guide. The check may be deposited in a user's bank account based on the image. Any technique for sending the image to the financial institution may be used.
-
公开(公告)号:US12131224B1
公开(公告)日:2024-10-29
申请号:US18057112
申请日:2022-11-18
CPC分类号: G06K7/1465 , G06K7/1413 , G06K7/1443 , G06T3/40 , G06T5/00 , G06T5/50 , G06T2207/20081
摘要: Systems and techniques for reading a structured identifier are provided. One technique involves obtaining a set of images of an item with a structured identifier. A region of interest (ROI) of the structured identifier within a first image of the set of images is determined. A second image comprising the ROI of the structured identifier is generated. An enhanced version of the second image is generated, based on processing the second image with at least one image restoration model. The structured identifier is decoded from the enhanced version of the second image to obtain data corresponding to the structured identifier.
-
100.
公开(公告)号:US12130940B2
公开(公告)日:2024-10-29
申请号:US17819829
申请日:2022-08-15
发明人: Christian Cote , Nidhin Davis
IPC分类号: G06F21/62 , G05B19/4155 , G06T7/00
CPC分类号: G06F21/6245 , G05B19/4155 , G06T7/0004 , G05B2219/33099 , G06F2221/2143
摘要: A system to physically remove data including customer personal information from mobile devices includes a computer; an input device to input to the computer a unique identifier associated with a board; a computer numerical control (CNC) machine controlled by the computer and configured to physically remove a predetermined chip from the board; a camera to record the CNC machine physically removing the predetermined chip from the board; and a memory to store a first file comprising the camera's recording and to store a second file comprising a record associating the unique identifier associated with the board to the camera's recording.
-
-
-
-
-
-
-
-
-