公开(公告)号：US20200349189A1

公开(公告)日：2020-11-05

申请号：US16929429

申请日：2020-07-15

Applicant: Adobe Inc.

Inventor： Xiaohui Shen ,  Zhe Lin ,  Kalyan Krishna Sunkavalli ,  Hengshuang Zhao ,  Brian Lynn Price

IPC: G06F16/58 ,  G06N3/08 ,  G06F16/51

Abstract: Compositing aware digital image search techniques and systems are described that leverage machine learning. In one example, a compositing aware image search system employs a two-stream convolutional neural network (CNN) to jointly learn feature embeddings from foreground digital images that capture a foreground object and background digital images that capture a background scene. In order to train models of the convolutional neural networks, triplets of training digital images are used. Each triplet may include a positive foreground digital image and a positive background digital image taken from the same digital image. The triplet also contains a negative foreground or background digital image that is dissimilar to the positive foreground or background digital image that is also included as part of the triplet.

公开(公告)号：US20190361994A1

公开(公告)日：2019-11-28

申请号：US15986401

申请日：2018-05-22

Applicant: Adobe Inc.

Inventor： Xiaohui Shen ,  Zhe Lin ,  Kalyan Krishna Sunkavalli ,  Hengshuang Zhao ,  Brian Lynn Price

IPC: G06F17/30 ,  G06N3/08

Abstract: Compositing aware digital image search techniques and systems are described that leverage machine learning. In one example, a compositing aware image search system employs a two-stream convolutional neural network (CNN) to jointly learn feature embeddings from foreground digital images that capture a foreground object and background digital images that capture a background scene. In order to train models of the convolutional neural networks, triplets of training digital images are used. Each triplet may include a positive foreground digital image and a positive background digital image taken from the same digital image. The triplet also contains a negative foreground or background digital image that is dissimilar to the positive foreground or background digital image that is also included as part of the triplet.

公开(公告)号：US11263259B2

公开(公告)日：2022-03-01

申请号：US16929429

申请日：2020-07-15

Applicant: Adobe Inc.

Inventor： Xiaohui Shen ,  Zhe Lin ,  Kalyan Krishna Sunkavalli ,  Hengshuang Zhao ,  Brian Lynn Price

IPC: G06F16/00 ,  G06F16/58 ,  G06N3/08 ,  G06F16/51

Abstract: Compositing aware digital image search techniques and systems are described that leverage machine learning. In one example, a compositing aware image search system employs a two-stream convolutional neural network (CNN) to jointly learn feature embeddings from foreground digital images that capture a foreground object and background digital images that capture a background scene. In order to train models of the convolutional neural networks, triplets of training digital images are used. Each triplet may include a positive foreground digital image and a positive background digital image taken from the same digital image. The triplet also contains a negative foreground or background digital image that is dissimilar to the positive foreground or background digital image that is also included as part of the triplet.

公开(公告)号：US10747811B2

公开(公告)日：2020-08-18

申请号：US15986401

申请日：2018-05-22

Applicant: Adobe Inc.

Inventor： Xiaohui Shen ,  Zhe Lin ,  Kalyan Krishna Sunkavalli ,  Hengshuang Zhao ,  Brian Lynn Price

IPC: G06F16/00 ,  G06F16/58 ,  G06N3/08 ,  G06F16/51

Abstract: Compositing aware digital image search techniques and systems are described that leverage machine learning. In one example, a compositing aware image search system employs a two-stream convolutional neural network (CNN) to jointly learn feature embeddings from foreground digital images that capture a foreground object and background digital images that capture a background scene. In order to train models of the convolutional neural networks, triplets of training digital images are used. Each triplet may include a positive foreground digital image and a positive background digital image taken from the same digital image. The triplet also contains a negative foreground or background digital image that is dissimilar to the positive foreground or background digital image that is also included as part of the triplet.