公开(公告)号：US12236534B1

公开(公告)日：2025-02-25

申请号：US18444013

申请日：2024-02-16

Applicant: Google LLC

Inventor： Charles Goran ,  Ilies Ghanzouri ,  Cardin Everett Moffett ,  Julien Benjamin Brette ,  Santiago David Lopez Lopez ,  Marcos Seefelder de Assis Araujo ,  Daniel Joseph Filip

IPC: G06T19/00 ,  G01C21/36

Abstract: The present disclosure provides methods, systems, and devices for projecting user-generated media content into three-dimensional immersive views. A system can obtain a three-dimensional representation of a location generated based on a plurality of images. The system can access user-generated media content associated with the location. The system can receive path information representing a path through the three-dimensional representation of the location. The system can select one or more pieces of user-generated media content based on the path information. The system can integrate the one or more pieces of user-generated media content into the three-dimensional representation of the location based on the path information and a portion of the three-dimensional representation to be displayed to a user, wherein the pieces of user-generated media content are presented within visual pop-outs in the three-dimensional representation. The system can provide the three-dimensional representation of the location for display to a user.

公开(公告)号：US20250166311A1

公开(公告)日：2025-05-22

申请号：US18517455

申请日：2023-11-22

Applicant: Google LLC

Inventor： Carlos Montero, JR. ,  Marcos Seefelder de Assis Araujo ,  Cardin Everett Moffett ,  Charles Goran

IPC: G06T19/00 ,  G06F16/787 ,  G06T7/10 ,  H04N13/354

Abstract: Systems and methods for generating and providing a virtual walkthrough interface can include generating a virtual walkthrough video based on view synthesis renderings generated by neural radiance field model. The neural radiance field model can be trained based on a plurality of images of an environment and may generate the view synthesis renderings based on processing positions along a determined walkthrough path. The generated virtual walkthrough video can then be scrubbed through to provide the virtual walkthrough interface.