公开(公告)号：US20250117119A1

公开(公告)日：2025-04-10

申请号：US18909927

申请日：2024-10-08

Applicant: Meta Platforms Technologies, LLC

Inventor： Bryan Wang ,  Rajinder Sodhi ,  Yan Xu ,  Zhaoyang Lv ,  Yuliang Li

IPC: G06F3/0484 ,  G06F3/0488 ,  G06F40/40 ,  G11B27/031

Abstract: Systems and methods for language augmented video editing are disclosed. A method includes presenting a video editing assistant (e.g., via a communicatively coupled display and/or speaker). The method includes, in response to receiving a request from a user to create adaptive video content that satisfies a set of characteristics identified based on the request i) analyzing, using a first machine-learning model, existing video content to identify portions of the existing video content that satisfy the set of characteristics and ii) for each portion of the existing video content that satisfies the set of characteristics, create adaptive video content using a respective portion of the existing video content that satisfies the set of characteristics. The method includes generating, using a second machine-learning model, descriptions of the adaptive video content and presenting the adaptive video content and the descriptions of the adaptive video content.

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.