公开(公告)号：US10957063B2

公开(公告)日：2021-03-23

申请号：US15935976

申请日：2018-03-26

Applicant: Adobe Inc. ,  Portland State University

Inventor： Stephen DiVerdi ,  Cuong Nguyen ,  Aaron Hertzmann ,  Feng Liu

IPC: G06T7/593 ,  G06T7/73 ,  G06T7/529 ,  G06T19/00

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified video content to reduce depth conflicts between user interface elements and video objects. For example, the disclosed systems can analyze an input video to identify feature points that designate objects within the input video and to determine the depths of the identified feature points. In addition, the disclosed systems can compare the depths of the feature points with a depth of a user interface element to determine whether there are any depth conflicts. In response to detecting a depth conflict, the disclosed systems can modify the depth of the user interface element to reduce or avoid the depth conflict. Furthermore, the disclosed systems can apply a blurring effect to an area around a user interface element to reduce the effect of depth conflicts.

公开(公告)号：US20190295280A1

公开(公告)日：2019-09-26

申请号：US15935976

申请日：2018-03-26

Applicant: Adobe Inc. ,  Portland State University

Inventor： Stephen DiVerdi ,  Cuong Nguyen ,  Aaron Hertzmann ,  Feng Liu

IPC: G06T7/593 ,  G06T7/529 ,  G06T7/73 ,  G06T19/00

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified video content to reduce depth conflicts between user interface elements and video objects. For example, the disclosed systems can analyze an input video to identify feature points that designate objects within the input video and to determine the depths of the identified feature points. In addition, the disclosed systems can compare the depths of the feature points with a depth of a user interface element to determine whether there are any depth conflicts. In response to detecting a depth conflict, the disclosed systems can modify the depth of the user interface element to reduce or avoid the depth conflict. Furthermore, the disclosed systems can apply a blurring effect to an area around a user interface element to reduce the effect of depth conflicts.

公开(公告)号：US20250119624A1

公开(公告)日：2025-04-10

申请号：US18894443

申请日：2024-09-24

Applicant: ADOBE INC.

Inventor： Seoung Wug Oh ,  Mingi Kwon ,  Joon-Young Lee ,  Yang Zhou ,  Difan Liu ,  Haoran Cai ,  Baqiao Liu ,  Feng Liu

IPC: H04N21/81

Abstract: A method, apparatus, non-transitory computer readable medium, and system for generating synthetic videos includes obtaining an input prompt describing a video scene. The embodiments then generate a plurality of frame-wise token embeddings corresponding to a sequence of video frames, respectively, based on the input prompt. Subsequently, embodiments generate, using a video generation model, a synthesized video depicting the video scene. The synthesized includes a plurality of images corresponding to the sequence of video frames.

公开(公告)号：US20250117971A1

公开(公告)日：2025-04-10

申请号：US18816693

申请日：2024-08-27

Applicant: ADOBE INC.

Inventor： Feng Liu ,  Zhengang Li ,  Yan Kang ,  Yuchen Liu ,  Difan Liu ,  Tobias Hinz

IPC: G06T11/00 ,  G06T3/4046 ,  G06T3/4053 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

Abstract: A method, apparatus, non-transitory computer readable medium, apparatus, and system for video generation include first obtaining a training set including a training video. Then, embodiments initialize a video generation model, sample a subnet architecture from an architecture search space, and a identify a subset of the weights of the video generation model based on the sampled subnet architecture. Subsequently, embodiments train, based on the training video, a subnet of the video generation model to generate synthetic video data. The subnet includes a subset of the weights of the video generation model.