公开(公告)号：US11816181B2

公开(公告)日：2023-11-14

申请号：US17190197

申请日：2021-03-02

Applicant: ADOBE INC.

Inventor： Aashish Misraa ,  Zhe Lin

IPC: G06V10/774 ,  G06F18/214 ,  G06T7/00 ,  G06F18/241 ,  G06V10/82 ,  G06V10/70

CPC classification number: G06F18/214 ,  G06F18/241 ,  G06T7/0002 ,  G06V10/774 ,  G06V10/82 ,  G06V10/87 ,  G06T2207/20081 ,  G06T2207/30168

Abstract: Systems and methods for image processing are described. Embodiments identify a training set including a first image that includes a ground truth blur classification and second image that includes a ground truth blur map, generate a first embedded representation of the first image and a second embedded representation of the second image using an image encoder, predict a blur classification of the first image based on the first embedded representation using a classification layer, predict a blur map of the second image based on the second embedded representation using a map decoder, compute a classification loss based on the predicted blur classification and the ground truth blur classification, train the image encoder and the classification layer based on the classification loss, compute a map loss based on the blur map and the ground truth blur map, and train the image encoder and the map decoder.

公开(公告)号：US12266181B2

公开(公告)日：2025-04-01

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: G06V20/40 ,  G06F18/214 ,  G06F18/23 ,  G06F18/25 ,  G06F40/205

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：US20220284236A1

公开(公告)日：2022-09-08

申请号：US17190197

申请日：2021-03-02

Applicant: ADOBE INC.

Inventor： Aashish Misraa ,  Zhe Lin

IPC: G06K9/62 ,  G06T7/00

Abstract: Systems and methods for image processing are described. Embodiments identify a training set including a first image that includes a ground truth blur classification and second image that includes a ground truth blur map, generate a first embedded representation of the first image and a second embedded representation of the second image using an image encoder, predict a blur classification of the first image based on the first embedded representation using a classification layer, predict a blur map of the second image based on the second embedded representation using a map decoder, compute a classification loss based on the predicted blur classification and the ground truth blur classification, train the image encoder and the classification layer based on the classification loss, compute a map loss based on the blur map and the ground truth blur map, and train the image encoder and the map decoder.