公开(公告)号：US20240119609A1

公开(公告)日：2024-04-11

申请号：US18484195

申请日：2023-10-10

Applicant: Meta Platforms Technologies, LLC

Inventor： Michael Goesele ,  Richard Andrew Newcombe ,  Yujia Chen ,  Florian Eddy Robert Ilg ,  Daniel Andersen ,  Chao Li ,  Simon Gareth Green

IPC: G06T7/292 ,  G06N3/02 ,  G06T7/246

CPC classification number: G06T7/292 ,  G06N3/02 ,  G06T7/246

Abstract: A distributed imaging system for augmented reality devices is disclosed. The system includes a computing module in communication with a plurality of spatially distributed sensing devices. The computing module is configured to process input images from the sensing devices based on performing a local feature matching computation to generate corresponding first output images. The computing module is further configured to process the input images based on performing an optical flow correspondence computation to generate corresponding second output images. The computing module is further configured to computationally combine first and second output images to generate third output images.

公开(公告)号：US12243273B2

公开(公告)日：2025-03-04

申请号：US17571285

申请日：2022-01-07

Applicant: META PLATFORMS TECHNOLOGIES, LLC

Inventor： Zhaoyang Lv ,  Miroslava Slavcheva ,  Tianye Li ,  Michael Zollhoefer ,  Simon Gareth Green ,  Tanner Schmidt ,  Michael Goesele ,  Steven John Lovegrove ,  Christoph Lassner ,  Changil Kim

IPC: G06T7/00

Abstract: In one embodiment, a method includes initializing latent codes respectively associated with times associated with frames in a training video of a scene captured by a camera. For each of the frames, a system (1) generates rendered pixel values for a set of pixels in the frame by querying NeRF using the latent code associated with the frame, a camera viewpoint associated with the frame, and ray directions associated with the set of pixels, and (2) updates the latent code associated with the frame and the NeRF based on comparisons between the rendered pixel values and original pixel values for the set of pixels. Once trained, the system renders output frames for an output video of the scene, wherein each output frame is rendered by querying the updated NeRF using one of the updated latent codes corresponding to a desired time associated with the output frame.