公开(公告)号：US20230162502A1

公开(公告)日：2023-05-25

申请号：US17531568

申请日：2021-11-19

Applicant: Adobe Inc.

Inventor： Shivam Nalin PATEL ,  Kshitiz GARG ,  Han GUO ,  Ali AMINIAN ,  Aashish MISRAA

IPC: G06K9/00 ,  G06K9/62 ,  G06F40/205

CPC classification number: G06K9/00765 ,  G06K9/6289 ,  G06K9/00744 ,  G06K9/6218 ,  G06F40/205 ,  G06K9/6256

Abstract: Embodiments are disclosed for receiving a user input and an input video comprising multiple frames. The method may include extracting a text feature from the user input. The method may further include extracting a plurality of image features from the frames. The method may further include identifying one or more keyframes from the frames that include the object. The method may further include clustering one or more groups of the one or more keyframes. The method may further include generating a plurality of segmentation masks for each group. The method may further include determining a set of reference masks corresponding to the user input and the object. The method may further include generating a set of fusion masks by combining the plurality of segmentation masks and the set of reference masks. The method may further include propagating the set of fusion masks and outputting a final set of masks.

公开(公告)号：US20240153303A1

公开(公告)日：2024-05-09

申请号：US17981985

申请日：2022-11-07

Applicant: ADOBE INC.

Inventor： Ali AMINIAN ,  Aashish Kumar MISRAA ,  Kshitiz GARG ,  Aseem AGARWALA

IPC: G06V40/16 ,  G06T7/20 ,  G06V10/30 ,  G06V10/762 ,  G06V20/40

CPC classification number: G06V40/161 ,  G06T7/20 ,  G06V10/30 ,  G06V10/762 ,  G06V20/49 ,  G06V40/171 ,  G06T2207/30201 ,  G06V2201/07

Abstract: Some aspects of the technology described herein perform identity identification on faces in a video. Object tracking is performed on detected faces in frames of a video to generate tracklets. Each tracklet comprises a sequence of consecutive frames in which each frame includes a detected face for a person. The tracklets are clustered using face feature vectors for detected faces of each tracklet to generate a plurality of clusters. Information is stored in an identity datastore, including a first identifier for a first identity in association with an indication of frames from tracklets in a first cluster from the plurality of clusters.

公开(公告)号：US20230377339A1

公开(公告)日：2023-11-23

申请号：US17751322

申请日：2022-05-23

Applicant: Adobe Inc.

Inventor： Han GUO ,  Kshitiz GARG ,  Ali AMINIAN ,  Aashish MISRAA ,  William MARINO ,  Nicolas HUYNH THIEN

IPC: G06V20/40 ,  G06V10/774 ,  G06V40/16 ,  G06T11/60

CPC classification number: G06V20/46 ,  G06V10/774 ,  G06V40/169 ,  G06T11/60

Abstract: Embodiments are disclosed for generating temporally consistent manipulated videos. A method of generating temporally consistent manipulated videos comprises receiving a target appearance and an input digital video including a plurality of frames, generating a plurality of target appearance frames from the plurality of frames, training a video prediction network to generate a digital video wherein a subject of the digital video has its appearance modified to match the target appearance, providing the input digital video to the video prediction network, and generating, by the video prediction network, an output digital video wherein the subject of the output digital video has its appearance modified to match the target appearance.