-
公开(公告)号：US20240303874A1
公开(公告)日：2024-09-12
申请号：US18434317
申请日：2024-02-06
发明人： Chun-Wei Chan
摘要： Systems and methods for providing interactive content may include one or more processors which receive first content of a content stream from a content provider, where the first content is for rendering via a media player of one or more user devices. The processor(s) may determine a context of the first content, and generate, via one or more machine learning models, second content which corresponds to the first content. The processor(s) may transmit the second content to an application of the one or more user devices, for rendering the second content via the application.
-
公开(公告)号：US12039793B2
公开(公告)日：2024-07-16
申请号：US17689164
申请日：2022-03-08
发明人： Chun-Wei Chan
CPC分类号： G06V20/647 , G06T7/55 , G06T7/74 , G06T11/001 , G06T15/04 , G06T19/20 , G06V10/74 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2219/004 , G06T2219/2008
摘要： Methods and systems described herein are directed to creating an artificial reality environment having elements automatically created from source images. In response to a creation system receiving the source images, the system can employ a multi-layered comparative analysis to obtain virtual object representations of objects depicted in the source images. A first set of the virtual objects can be selected from a library by matching identifiers for the depicted objects with tags on virtual objects in the library. A second set of virtual objects can be objects for which no candidate first virtual objects was adequately matched in the library, prompting the creation of a virtual object by generating depth data and skinning a resulting 3D mesh based on the source images. Having determined the virtual objects, the system can compile them into the artificial reality environment according to relative locations determined from the source images.
-
搜索结果
2 条记录 (耗时 0.015 秒)
