公开(公告)号：US12094593B2

公开(公告)日：2024-09-17

申请号：US18198446

申请日：2023-05-17

Applicant: Konica Minolta, Inc.

Inventor： Takafumi Nanjo

IPC: G06T1/00 ,  G06T11/00 ,  G16H30/20

CPC classification number: G16H30/20 ,  G06T11/00 ,  G06T2210/32 ,  G06T2210/41

Abstract: A medical image display system includes a server, and a medical image display terminal that communicates with the server. The server includes a storage that stores medical image data in a storage format, and a first transmitter that transmits the medical image data in the storage format to the medical image display terminal. The medical image display terminal includes a first hardware processor that converts the medical image data in the storage format transmitted from the server into medical image data in a viewing format that is viewable on a web browser, and a display that displays a medical image based on the medical image data in the viewing format on the web browser.

公开(公告)号：US20240290037A1

公开(公告)日：2024-08-29

申请号：US18573644

申请日：2022-07-07

Applicant: Hover Inc.

Inventor： Kerry Gould ,  Jeffrey Sommers ,  Harsh Barbhaiya

IPC: G06T17/20 ,  G06T5/70 ,  G06T15/00 ,  G06T15/80 ,  G06T19/20

CPC classification number: G06T17/20 ,  G06T5/70 ,  G06T15/005 ,  G06T15/80 ,  G06T19/20 ,  G06T2210/04 ,  G06T2210/32 ,  G06T2219/2012

Abstract: Methods, storage media, and systems for integrating disparate data streams of a current scan to generate visual cues of the current scan are disclosed. Exemplary implementations may: receive, from a data capture device, captured visual data and captured depth data of a current scan of an environment; generate a first plurality of masks based on the captured depth data; generate a depth propagation based on the first plurality of masks; generate augmented visual data based on the captured visual data, the first plurality of masks, and the depth propagation; and display, on a display of the data capture device, the augmented visual data.

公开(公告)号：US20240135595A1

公开(公告)日：2024-04-25

申请号：US18489359

申请日：2023-10-17

Applicant: Electronics and Telecommunications Research Institute

Inventor： Da Yun NAM ,  Hyun Cheol KIM ,  Jeong Il SEO ,  Seong Yong LIM ,  Chae Eun RHEE ,  Gwang Cheol RYU ,  Yong Wook SEO ,  Hyun Min JUNG

IPC: G06T9/00 ,  G06T19/00

CPC classification number: G06T9/001 ,  G06T19/00 ,  G06T2210/32 ,  G06T2210/36

Abstract: The present invention relates to a method and apparatus for encoding a displacement video using image tiling. A method for encoding multi-dimensional data according to an embodiment of the present disclosure may comprise: converting the multi-dimensional data into one or more frames with two-dimensional characteristics; generating one or more frame groups by grouping the one or more frames with pre-configured number units; reconstructing frames belonging to each frame group into a tiled frame; and generating a bitstream by encoding the tiled frame. Here, the tiled frame may be constructed with one or more blocks, and each block may be constructed by rearranging pixels existing at the same location in the frames.

公开(公告)号：US20240087267A1

公开(公告)日：2024-03-14

申请号：US17994752

申请日：2022-11-28

Applicant: Shopify Inc.

Inventor： Russ MASCHMEYER ,  Eric Andrew FLORENZANO ,  Brennan LETKEMAN ,  Diego Macario BELLO ,  Daniel BEAUCHAMP

IPC: G06T19/20 ,  G06F3/04815 ,  G06F3/04845 ,  G06T11/00 ,  G06T19/00

CPC classification number: G06T19/20 ,  G06F3/04815 ,  G06F3/04845 ,  G06T11/00 ,  G06T19/006 ,  G06T2200/24 ,  G06T2210/32 ,  G06T2219/2004

Abstract: A computer-implemented is disclosed. The method includes: generating an augmented reality (AR) scene that includes a virtual 3D representation of a product and a view of a first graphical user interface; monitoring user interactions with the virtual 3D representation of the product based on detected gestures of the user; determining modifications to the virtual 3D representation of the product based on the monitored user interactions; presenting, in the AR scene, a modified 3D representation of the product; converting the modified 3D representation of the product to a 2D image; and causing the 2D image to be displayed at a defined location of the first graphical user interface in AR.

公开(公告)号：US20240013469A1

公开(公告)日：2024-01-11

申请号：US18219441

申请日：2023-07-07

Applicant: Glenfly Tech Co., Ltd.

Inventor： Lei LI ,  Fengxia WU

IPC: G06T15/00 ,  G06T11/00

CPC classification number: G06T15/005 ,  G06T11/001 ,  G06T2210/32 ,  G06T2210/44

Abstract: Programmable pixel blending method and apparatus, computer device, storage medium and computer program product are provided. The method includes: performing rasterization on a first triangle, a second triangle, and a third triangle via the raster unit to obtain triangle coverage information of each triangle; sending the triangle coverage information to the warp assembly unit and the warp reorder unit respectively; assembling, by the warp assembly unit, the first triangle and the second triangle into a first warp, and requesting a warp from a warp request interface based on information of the first warp; executing the first warp based on a warp information cache, a warp synchronization unit, the warp reorder unit, the pixel operation unit, the interpolation unit, and the execution unit; after the first warp is executed, continuing to assemble, by the warp assembly unit, the third triangle and completing a rendering of the third triangle.

公开(公告)号：US11854110B2

公开(公告)日：2023-12-26

申请号：US17558113

申请日：2021-12-21

Applicant: Rockwell Collins, Inc.

Inventor： Jeff M. Henry ,  Srinath A. Nandakumar

IPC: G06T11/20 ,  G06T7/50 ,  G06T7/70 ,  G06V30/41 ,  G06V30/242 ,  G06V30/14 ,  G06F3/14 ,  G06T7/60 ,  G06T11/60

CPC classification number: G06T11/203 ,  G06F3/14 ,  G06T7/50 ,  G06T7/60 ,  G06T7/70 ,  G06T11/60 ,  G06V30/1448 ,  G06V30/242 ,  G06V30/41 ,  G06T2200/28 ,  G06T2207/30176 ,  G06T2210/12 ,  G06T2210/32

Abstract: A system may include a processor configured to: obtain an image of an airport terminal chart; based on a latitudinal set of characters, determine a latitude for each line of latitude; based on the latitude for each line of latitude and a first image distance between the lines of latitude, determine a first ratio of latitudinal degrees between the lines of latitude to the first image distance; based on a longitudinal set of characters, determine a longitude for each line of longitude; based on the longitude for each line of longitude and a second image distance between the lines of longitude, determine a second ratio of longitudinal degrees between the lines of longitude to the second image distance; and output information associated with the first ratio, the second ratio, the determined latitude for each line of latitude, and the determined longitude for each line of longitude.

公开(公告)号：US20230377214A1

公开(公告)日：2023-11-23

申请号：US18320857

申请日：2023-05-19

Applicant: DISNEY ENTERPRISES, INC. ,  ETH Zürich (Eidgenössische Technische Hochschule Zürich)

Inventor： Manuel Jakob KANSY ,  Anton Julien RAËL ,  Jacek Krzysztof NARUNIEC ,  Christopher Richard SCHROERS ,  Romann Matthew WEBER

IPC: G06T11/00 ,  G06T5/00 ,  G06V40/16 ,  G06V10/82

CPC classification number: G06T11/00 ,  G06T5/002 ,  G06V40/171 ,  G06V10/82 ,  G06T2210/32 ,  G06T2207/20081 ,  G06V2201/10 ,  G06T2207/30201

Abstract: One embodiment of the present invention sets forth a technique for performing identity-preserving image generation. The technique includes converting an identity image depicting a facial identity into an identity embedding. The technique further includes generating a combined embedding based on the identity embedding and a diffusion iteration identifier. The technique further includes converting, using a neural network and based on the combined embedding, a first input image that includes first noise into a first predicted image depicting one or more facial features that include one or more first facial identity features, wherein the one or more first facial identity features correspond to one or more respective second facial identity features of the identity image and are based at least on the identity embedding.

公开(公告)号：US20230368471A1

公开(公告)日：2023-11-16

申请号：US18196647

申请日：2023-05-12

Applicant: Joseph Isaac Gratz

Inventor： Joseph Isaac Gratz

IPC: G06T19/00 ,  G06T7/70 ,  G06T17/00 ,  H04N21/2343

CPC classification number: G06T19/00 ,  G06T7/70 ,  G06T17/00 ,  H04N21/23439 ,  G06T2210/32 ,  G06T2207/10016 ,  G06T2200/24 ,  G06T2207/30221

Abstract: Methods and systems are disclosed for the conversion of a two-dimensional video media into a rendered three-dimensional video media, said conversion commonly being facilitated by at least one database having frames of pre-rendered three-dimensional recreations containing at least one rendered model in at least one location and in at least one pose within a rendered area, and having a means for selecting the pre-rendered three-dimensional frame from the database that most closely resembles the two-dimensional video media. Further embodiments include interactable elements in the rendered three-dimensional video media, said interactable elements displaying information when the interactable element is manipulated by a user.

公开(公告)号：US20230334831A1

公开(公告)日：2023-10-19

申请号：US17987452

申请日：2022-11-15

Applicant: Hyundai Motor Company ,  Kia Corporation

Inventor： Minkooc Wee ,  Sung Hoon Bang

IPC: G06V10/774 ,  G06T17/00

CPC classification number: G06V10/774 ,  G06T17/00 ,  G06T2210/32 ,  G06V2201/12

Abstract: Provided is a training dataset generating system including: a communicator to receive a two-dimensional (2D) image obtained by photographing a target object; and a controller configured to generate, based on the 2D image and based on three-dimensional (3D) data for the target object, a training dataset comprising a synthetic image and comprising labeling information, wherein the controller is configured to generate the training data set by: generating, based on the 3D data, a rendered image, generating the synthetic image, based on the 2D image and the rendered image, through deep learning training, extracting, based on at least one of the 3D data or the rendered image, the labeling information for the target object, and generating the training dataset.

公开(公告)号：US11688136B2

公开(公告)日：2023-06-27

申请号：US17249441

申请日：2021-03-02

Applicant: Snap Inc.

Inventor： Georgios Papandreou ,  Iason Kokkinos

IPC: G06T17/20 ,  G06N20/00

CPC classification number: G06T17/20 ,  G06N20/00 ,  G06T2210/32 ,  G06T2210/56 ,  G06T2219/2016

Abstract: Systems and methods for reconstructing 3D models of human bodies from 2D images that counts for perspective and/or distortion effects are provided. The systems and methods include reconstructing a three-dimensional model of an object in a three-dimensional scene from a two-dimensional image comprising an image of the object. The systems and methods include determining an absolute depth of a key point of the object in the image; determining, using the absolute depth of the key point, a three-dimensional position of the key point in the three-dimensional scene; generating, using a neural network, a three-dimensional representation of the object, the three-dimensional representation comprising mesh nodes defined in a coordinate system relative to the key point; and positioning the three-dimensional representation of the object in the scene based on the position of the key point by applying a position dependent rotation to the three-dimensional object.