-
公开(公告)号：US11694392B2
公开(公告)日：2023-07-04
申请号：US16372882
申请日：2019-04-02
Applicant: Apple Inc.
Inventor： Daniel Kurz , Gowri Somanath , Tobias Holl
CPC classification number: G06T15/50 , G06T7/40 , G06T7/73 , G06T19/006
Abstract: Various implementations disclosed herein include devices, systems, and methods that render a reflective surface of a computer-generated reality (“CGR”) object based on synthesis in a CGR environment. In order to render a reflective surface of the CGR object, one exemplary implementation involves synthesizing an environment map of a CGR environment representing a portion of a physical scene based on observed characteristics of the physical scene. In an implementation, generation of a complete environment map includes identifying pixels of the environment map with no corresponding texture and generating synthesized texture based on textural information associated with one or more camera images of the physical scene. In an implementation, a CGR object is rendered in the CGR environment, wherein an appearance of a reflective surface of the CGR object is determined based on the complete environment map of the CGR environment.
-
公开(公告)号：US11636578B1
公开(公告)日：2023-04-25
申请号：US17238285
申请日：2021-04-23
Applicant: Apple Inc.
Inventor： Daniel Kurz , Gowri Somanath , Tobias Holl
Abstract: Various implementations disclosed herein include devices, systems, and methods that complete content for a missing part of an image of an environment. For example, an example process may include obtaining an image including defined content and missing parts for which content is undefined, determining a spatial image transformation for the image based on the defined content and the missing parts of the image, altering the image by applying the spatial image transformation, and completing the altered image.
-
公开(公告)号：US11423308B1
公开(公告)日：2022-08-23
申请号：US17021340
申请日：2020-09-15
Applicant: Apple Inc.
Inventor： Gowri Somanath , Daniel Kurz
Abstract: Implementations disclosed herein provide systems and methods that use classification-based machine learning to generate perceptually-plausible content for a missing part (e.g., some or all) of an image. The machine learning model may be trained to generate content for the missing part that appears plausible by learning to generate content that cannot be distinguished from real image content, for example, using adversarial loss-based training. To generate the content, a probabilistic classifier may be used to select color attribute values (e.g., RGB values) for each pixel of the missing part of the image. To do so, a pixel color attribute is segmented into a number of bins (e.g., value ranges) that are used as classes. The classifier determines probabilities for each of the bins of a color attribute for each pixel and generates the content by selecting the bin having the highest probability for each color attribute for each pixel.
-
公开(公告)号：US12002165B1
公开(公告)日：2024-06-04
申请号：US17412507
申请日：2021-08-26
Applicant: Apple Inc.
Inventor： Daniel Kurz , Gowri Somanath , Tobias Holl
CPC classification number: G06T19/006 , G06T15/506 , G06T19/20 , G06T2215/16
Abstract: Various implementations disclosed herein include devices, systems, and methods that use light probes to facilitate the display of virtual objects in 3D environments. A light probe provides lighting information that describes light incident on a point in space in a 3D environment. For example, a light probe may describe such incident light using an environment map. Such lighting information can be used to provide realistic appearances for objects placed at or near light probe locations in the 3D environment. Implementations disclosed herein determine the light probe locations in real-time or other 3D environments that are generated based on a live physical environment. A digital representation of the live physical environment is used to determine where to position the light probes, how many light probes to use, and/or various light probe attributes.
-
-
-
Search Results
4
records
(took 0.011 seconds)
