公开(公告)号：US20240380931A1

公开(公告)日：2024-11-14

申请号：US18646422

申请日：2024-04-25

Applicant: Outward, Inc.

Inventor： Clarence Chui

IPC: H04N21/234 ,  H04N21/44 ,  H04N21/84

Abstract: Techniques for rendering a scene are disclosed. In some embodiments, a scene definition is modified to generate a modified scene definition based at least in part on a current state of a local database at a device. The modified scene definition is constrained to include references to objects locally available in the local database, and at least one object referenced in the scene definition is substituted with a different object in the modified scene definition that is locally available in the local database. The scene is rendered at the device according to the modified scene definition.

公开(公告)号：US20240346780A1

公开(公告)日：2024-10-17

申请号：US18639638

申请日：2024-04-18

Applicant: Outward, Inc.

Inventor： Clarence Chui

IPC: G06T19/00 ,  G06T11/00 ,  G06V20/64 ,  H04N7/01 ,  H04N21/2343 ,  H04N21/4223 ,  H04N21/81 ,  H04N23/80

CPC classification number: G06T19/006 ,  G06T11/00 ,  G06V20/64 ,  H04N7/0125 ,  H04N21/234318 ,  H04N21/4223 ,  H04N21/8126 ,  H04N23/80

Abstract: Techniques for delivering virtualized content are disclosed. In some embodiments, elements in source content are mapped to a set of corresponding database objects, and the set of database objects is modified to generate a virtualized version of the source content. A specification of the virtualized version of the source content is provided to an output device in response to a request from the output device for the source content.

公开(公告)号：US20240331304A1

公开(公告)日：2024-10-03

申请号：US18741330

申请日：2024-06-12

Applicant: Outward, Inc.

Inventor： Clarence Chui

IPC: G06T19/00 ,  G06T17/00 ,  G06T19/20 ,  G06V20/00 ,  G06V20/20 ,  G06V20/40 ,  G06V20/64 ,  G06V20/70 ,  H04N21/84

CPC classification number: G06T19/00 ,  G06T17/00 ,  G06T19/20 ,  G06V20/20 ,  G06V20/35 ,  G06V20/41 ,  G06V20/647 ,  G06V20/70 ,  H04N21/84 ,  G06T2219/004

Abstract: Techniques for tagging a scene are disclosed. In some embodiments, information about a scene is inferred by at least in part automatically interpreting a metric associated with the scene that is determined by analyzing data comprising a primitive form of the scene, wherein analyzed data comprising the primitive form of the scene comprises positions of three-dimensional objects in the scene. The scene is tagged with a tag comprising the inferred information.

公开(公告)号：US20240320901A1

公开(公告)日：2024-09-26

申请号：US18617374

申请日：2024-03-26

Applicant: Outward, Inc.

Inventor： Clarence Chui ,  Manu Parmar ,  Brook Aaron Seaton ,  Himanshu Jain

IPC: G06T15/20 ,  G06T5/50 ,  G06T7/32 ,  G06T17/00

CPC classification number: G06T15/205 ,  G06T5/50 ,  G06T7/32 ,  G06T17/00

Abstract: Techniques for generating an arbitrary view or perspective of an ensemble scene are disclosed. In some embodiments, in response to a received request for a prescribed perspective of an ensemble scene comprising a plurality of assets, an output image of the ensemble scene that approximates the requested prescribed perspective is generated using existing images of each of at least a subset of the plurality of assets.

公开(公告)号：US11989821B2

公开(公告)日：2024-05-21

申请号：US17090794

申请日：2020-11-05

Applicant: Outward, Inc.

Inventor： Clarence Chui ,  Manu Parmar ,  Amogh Subbakrishna Adishesha ,  Harshul Gupta ,  Avinash Venkata Uppuluri

IPC: G06K9/36 ,  G06F16/58 ,  G06T5/50 ,  G06T7/32 ,  G06T15/20

CPC classification number: G06T15/205 ,  G06F16/58 ,  G06T5/50 ,  G06T7/32

Abstract: A machine learning based image processing and generation framework is disclosed. In some embodiments, depth values of an object or asset in a received input image are at least in part determined using a machine learning based framework that is constrained to a known prescribed environment. Determined depth values facilitate generation of other views of the object or asset.

公开(公告)号：US20230260443A1

公开(公告)日：2023-08-17

申请号：US18140529

申请日：2023-04-27

Applicant: Outward, Inc.

Inventor： Clarence Chui ,  Christopher Murphy

IPC: G09G3/20 ,  G06T15/04 ,  G09G5/36 ,  G06T11/40 ,  G06T15/50

CPC classification number: G09G3/20 ,  G06T11/40 ,  G06T15/04 ,  G06T15/503 ,  G09G5/363 ,  G09G2370/022

Abstract: Two-dimensional compositing that preserves the curvatures of non-flat surfaces is disclosed. In some embodiments, a mapping is associated with a two-dimensional rendering that maps a potentially variable portion of the two-dimensional rendering to a canvas. The mapping is generated from a three-dimensional model of the potentially variable portion of the two-dimensional rendering. The potentially variable portion of the two-dimensional rendering is dynamically modified according to the mapping to reflect content comprising the canvas or edits received with respect to the canvas.

公开(公告)号：US20230121860A1

公开(公告)日：2023-04-20

申请号：US17966152

申请日：2022-10-14

Applicant: Outward, Inc.

Inventor： Clarence Chui ,  Manu Parmar ,  Avinash Venkata Uppuluri ,  Akshansh Chaudhry ,  Himanshu Jain ,  Andrew Pang ,  Lakshay Sharma ,  Brook Aaron Seaton ,  Alan Thomas Mackey

IPC: G06T19/20 ,  H04N23/69

Abstract: A content generation platform is generally described herein. More specifically, interactive image generation and techniques and features thereof are disclosed herein. One or more sets of images of a scene are captured in an imaging studio. The captured one or more sets of images of the scene are processed using one or more machine learning based networks to generate an interactive image of the scene comprising a plurality of interactive features. One or more of the plurality of interactive features of the generated interactive image may be modified or edited according to user preferences.

公开(公告)号：US20230120807A1

公开(公告)日：2023-04-20

申请号：US17966291

申请日：2022-10-14

Applicant: Outward, Inc.

Inventor： Avinash Venkata Uppuluri ,  Clarence Chui ,  Manu Parmar

IPC: H04N23/60 ,  H04N23/695 ,  H04N23/62 ,  H04N23/61 ,  H04N13/239 ,  H04N13/296 ,  G06T17/20

Abstract: A content generation platform is generally described herein. More specifically, interactive image generation and techniques and features thereof are disclosed herein. One or more sets of images of a scene are captured in an imaging studio. The captured one or more sets of images of the scene are processed using one or more machine learning based networks to generate an interactive image of the scene comprising a plurality of interactive features. One or more of the plurality of interactive features of the generated interactive image may be modified or edited according to user preferences.

公开(公告)号：US20230118647A1

公开(公告)日：2023-04-20

申请号：US17966302

申请日：2022-10-14

Applicant: Outward, Inc.

Inventor： Himanshu Jain ,  Clarence Chui ,  Manu Parmar ,  Akshansh Chaudhry ,  Lakshay Sharma ,  Brook Aaron Seaton

IPC: G06T19/00 ,  G06T15/04 ,  G06V20/20 ,  G06T15/50

Abstract: A content generation platform is generally described herein. More specifically, interactive image generation and techniques and features thereof are disclosed herein. One or more sets of images of a scene are captured in an imaging studio. The captured one or more sets of images of the scene are processed using one or more machine learning based networks to generate an interactive image of the scene comprising a plurality of interactive features. One or more of the plurality of interactive features of the generated interactive image may be modified or edited according to user preferences.

公开(公告)号：US11544829B2

公开(公告)日：2023-01-03

申请号：US16917688

申请日：2020-06-30

Applicant: Outward, Inc.

Inventor： Clarence Chui ,  Manu Parmar

IPC: G06K9/36 ,  G06T5/50 ,  G06T15/20

Abstract: Techniques for generating an arbitrary view of a scene from existing images of the scene are disclosed. In some embodiments, an image of a scene having a desired perspective is at least in part generated by populating some pixels of the image having the desired perspective using pixels obtained from a transformed existing image of the scene that is selected from a stored set of existing images associated with the scene and that is transformed to the desired perspective.