公开(公告)号：US20240378807A1

公开(公告)日：2024-11-14

申请号：US18683995

申请日：2022-03-30

Applicant: Sony Group Corporation

Inventor： Daiki YAMANAKA ,  Takashi SENO ,  Manabu KAWASHIMA

IPC: G06T17/05 ,  G06T3/067 ,  G06T5/20

Abstract: There is provided a device and the like that reduce the influence of an error set in each voxel in a three-dimensional grid map, during a process of transforming the three-dimensional grid map into a two-dimensional grid map. An information processing device according to one aspect of the present disclosure includes a transform unit. The transform unit performs a convolution process on a three-dimensional grid map and a template. The three-dimensional grid map and the template include a plurality of three-dimensional unit cells each having a value set therein. The transform unit performs the convolution process, to transform the three-dimensional grid map into a two-dimensional grid map including a plurality of two-dimensional unit cells each having a value set therein.

公开(公告)号：US12217389B2

公开(公告)日：2025-02-04

申请号：US18514340

申请日：2023-11-20

Applicant: QUIDIENT, LLC

Inventor： David Scott Ackerson ,  Donald J. Meagher ,  John K. Leffingwell

IPC: G06T3/4092 ,  G06T3/067 ,  G06T3/4076 ,  G06T9/40 ,  G06T19/00

Abstract: Methods and apparatus for systems using a scene codec are described, where systems are either providers or consumers of multi-way, just-in-time, only-as-needed scene data including subscenes and subscene increments. An example system using a scene codec includes a plenoptic scene database containing one or more digital models of scenes, where representations and organization of representations are distributable across multiple systems such that collectively the multiplicity of systems can represent scenes of almost unlimited detail. The system may further include highly efficient means for the processing of these representation and organizations of representation providing the just-in-time, only-as-needed subscenes and scene increments necessary for ensuring a maximally continuous user experience enabled by a minimal amount of newly provided scene information, where the highly efficient means include a spatial processing unit.

公开(公告)号：US20240412455A1

公开(公告)日：2024-12-12

申请号：US18416236

申请日：2024-01-18

Applicant: Vertex Software, Inc.

Inventor： Daniel Murray ,  James Zwica ,  Jeffrey Murray ,  Steven Ourada

IPC: G06T17/20 ,  G06F16/53 ,  G06F30/00 ,  G06F30/10 ,  G06T3/067 ,  G06T15/20

Abstract: Methods and apparatus to facilitate 3D object visualization and manipulation across multiple devices are disclosed. Example apparatus disclosed herein include a viewpoint determiner, a visible shard determiner, and a laminate assembler. The viewpoint determiner determines a viewpoint location of a viewpoint corresponding to a viewing device, the viewpoint location being in a reference frame of a three-dimensional (3D) model. The visible shard determiner determines a visible shard set of the 3D model based on the viewpoint location. The laminate assembler generates a two-dimensional (2D) image of the visible shard set.

公开(公告)号：US12067643B2

公开(公告)日：2024-08-20

申请号：US17078071

申请日：2020-10-22

Applicant: Baobab Studios Inc.

Inventor： Mikhail Stanislavovich Solovykh ,  Wei Wang ,  Nathaniel Christopher Dirksen ,  Lawrence David Cutler ,  Apostolos Lerios

IPC: G06T11/00 ,  G06T3/067 ,  G06T13/80 ,  G11B27/02 ,  H04N5/222 ,  H04N21/2343 ,  H04N21/81 ,  H04N21/854

CPC classification number: G06T11/00 ,  G06T3/067 ,  G06T13/80 ,  H04N5/2224 ,  H04N21/234336 ,  H04N21/8146 ,  H04N21/816 ,  H04N21/854 ,  G06T2200/24 ,  G06T2213/08 ,  G11B27/02

Abstract: Systems, methods, and non-transitory computer-readable media can obtain data associated with a computer-based experience. The computer-based experience can be based on interactive real-time technology. At least one virtual camera can be configured within the computer-based experience in an animation creation application. A plurality of shots that correspond to two-dimensional content can be generated from an edit cut of content captured by the at least one virtual camera in the animation creation application. Data associated with a two-dimensional version of the computer-based experience can be generated in a real-time engine based on the plurality of shots. The two-dimensional version can be rendered based on the generated data.

公开(公告)号：US20240394850A1

公开(公告)日：2024-11-28

申请号：US18670515

申请日：2024-05-21

Applicant: Disney Enterprises, Inc. ,  ETH Zürich (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)

Inventor： Marios Papas ,  Gerhard Roethlin ,  Tunc Ozan Aydin ,  Xianyao Zhang ,  Farnood Salehi ,  Shilin Zhu

IPC: G06T5/70 ,  G06T3/067 ,  G06T9/00 ,  G06T15/00

Abstract: A system includes a pre-processor configured to receive three-dimensional (3-D) image data, flatten the 3-D image data to produce corresponding two-dimensional (2-D) image data, and concatenate the 3-D image data and the corresponding 2-D image data to provide concatenated image data. The system further includes an encoder including one or more first neural networks (NNs), the encoder configured to use the one or more first NNs to encode the concatenated image data to provide encoded data, a decoder including one or more second NNs, the decoder configured to use the one or more second NNs to decode the encoded data to provide decoded data, and a reconstructor including a plurality of hybrid 2-D/3-D reconstructors configured to reconstruct the decoded data to provide a denoised 3-D output image corresponding to the 3-D image data.

公开(公告)号：US20240212282A1

公开(公告)日：2024-06-27

申请号：US18586377

申请日：2024-02-23

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Jinbiao LIU

IPC: G06T17/20 ,  G06T3/067 ,  G06V10/25

CPC classification number: G06T17/20 ,  G06T3/067 ,  G06V10/25

Abstract: This application relates to an image rendering method performed by a computer device, and further relates to the field of gaming technologies. The method includes: flattening an original object mesh model to obtain a flat mesh model, the original object mesh model being an original three-dimensional mesh model of a target virtual object; generating a patch model according to a bounding box patch of the flat mesh model; performing topological reconstruction on the patch model, to obtain a reconstructed mesh model, a quantity of surfaces of the reconstructed mesh model being less than a quantity of surfaces of the original object mesh model; and reconstructing a three-dimensional mesh model based on the reconstructed mesh model.

公开(公告)号：US20240193823A1

公开(公告)日：2024-06-13

申请号：US18584906

申请日：2024-02-22

Applicant: Baobab Studios Inc.

Inventor： Mikhail Stanislavovich Solovykh ,  Wei Wang ,  Nathaniel Christopher Dirksen ,  Lawrence David Cutler ,  Apostolos Lerios

IPC: G06T11/00 ,  G06T3/067 ,  G06T13/80 ,  G11B27/02 ,  H04N5/222 ,  H04N21/2343 ,  H04N21/81 ,  H04N21/854

CPC classification number: G06T11/00 ,  G06T3/067 ,  G06T13/80 ,  H04N5/2224 ,  H04N21/234336 ,  H04N21/8146 ,  H04N21/816 ,  H04N21/854 ,  G06T2200/24 ,  G06T2213/08 ,  G11B27/02

Abstract: Systems, methods, and non-transitory computer-readable media can obtain data associated with a computer-based experience. The computer-based experience can be based on interactive real-time technology. At least one virtual camera can be configured within the computer-based experience in a real-time engine. Data associated with an edit cut of the computer-based experience can be obtained based on content captured by the at least one virtual camera. A plurality of shots that correspond to two-dimensional content can be generated from the edit cut of the computer-based experience in the real-time engine. Data associated with a two-dimensional version of the computer-based experience can be generated with the real-time engine based on the plurality of shots. The two-dimensional version can be rendered based on the generated data.

公开(公告)号：US20240169475A1

公开(公告)日：2024-05-23

申请号：US18574628

申请日：2022-06-15

Applicant: Endless Technologies Ltd.

Inventor： Roi GINAT ,  Nimrod SANDLERMAN

IPC: G06T3/067 ,  G06T3/40 ,  G06T17/00

CPC classification number: G06T3/067 ,  G06T3/40 ,  G06T17/00

Abstract: A streaming 2D image of an object is by obtaining a 2D image of the object and a 3D measurement of the object from a first angle with respect to the object; creating a 3D model of the object using the 2D image and the 3D measurement; obtaining a streaming 3D measurement of the object from a second angle with respect to the object; and creating a streaming 2D image of the object, based on the 3D model of the object and the streaming 3D measurement, the streaming 2D image being created for a third angle with respect to the object, the first and the third angles being different from the second angle with respect to the object.

公开(公告)号：US20250061538A1

公开(公告)日：2025-02-20

申请号：US18805459

申请日：2024-08-14

Applicant: Electronics and Telecommunications Research Institute

Inventor： Youn Hee KIM ,  JooYoung LEE ,  Se Yoon JEONG ,  Jin Soo CHOI ,  Jung Won KANG

IPC: G06T3/067 ,  G06T3/4046

Abstract: A feature map encoding method according to the present disclosure may include generating a feature map from a multi-level feature group; and performing PCA (Picture Component Analysis) transform for the feature map. Here, generating the feature map comprises reshaping the multi-level feature group; and generating the feature map by merging a plurality of base units generated by the reshape.

公开(公告)号：US12205264B2

公开(公告)日：2025-01-21

申请号：US17503220

申请日：2021-10-15

Applicant: Cognex Corporation

Inventor： Hongwei Zhu ,  Daniel Moreno

IPC: G06T7/00 ,  G06T3/067 ,  G06V10/46

Abstract: This invention provides a system and method that efficiently detects objects imaged using a 3D camera arrangement by referencing a cylindrical or spherical surface represented by a point cloud, and measures variant features of an extracted object including volume, height, and center of mass, bounding box, and other relevant metrics. The system and method, advantageously, operates directly on unorganized and un-ordered points, requiring neither a mesh/surface reconstruction nor voxel grid representation of object surfaces in a point cloud. Based upon a cylinder/sphere reference model, an acquired 3D point cloud is flattened. Object (blob) detection is carried out in the flattened 3D space, and objects are converted back to the 3D space to compute the features, which can include regions that differ from the regular shape of the cylinder/sphere. Downstream utilization devices and/or processes, such as part reject mechanism and/or robot manipulators can act on the identified feature data.