公开(公告)号：US11880977B2

公开(公告)日：2024-01-23

申请号：US17313158

申请日：2021-05-06

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Scott Cohen ,  Marco Forte ,  Ning Xu

IPC: G06T7/11 ,  G06T7/136 ,  G06T7/194 ,  G06T7/90 ,  G06T3/40 ,  G06N3/088 ,  G06N3/045 ,  G06N3/02 ,  G06N20/00

CPC classification number: G06T7/11 ,  G06N3/045 ,  G06N3/088 ,  G06T3/40 ,  G06T7/136 ,  G06T7/194 ,  G06T7/90 ,  G06N3/02 ,  G06N20/00 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20096 ,  G06T2207/20104

Abstract: Techniques are disclosed for deep neural network (DNN) based interactive image matting. A methodology implementing the techniques according to an embodiment includes generating, by the DNN, an alpha matte associated with an image, based on user-specified foreground region locations in the image. The method further includes applying a first DNN subnetwork to the image, the first subnetwork trained to generate a binary mask based on the user input, the binary mask designating pixels of the image as background or foreground. The method further includes applying a second DNN subnetwork to the generated binary mask, the second subnetwork trained to generate a trimap based on the user input, the trimap designating pixels of the image as background, foreground, or uncertain status. The method further includes applying a third DNN subnetwork to the generated trimap, the third subnetwork trained to generate the alpha matte based on the user input.

公开(公告)号：US20220114705A1

公开(公告)日：2022-04-14

申请号：US17557431

申请日：2021-12-21

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Yinan Zhao ,  Scott David Cohen

IPC: G06T5/00 ,  G06T5/50 ,  G06T11/40 ,  G06T7/33 ,  G06N3/08 ,  G06T3/00 ,  G06N3/04

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.

公开(公告)号：US20220092790A1

公开(公告)日：2022-03-24

申请号：US17544048

申请日：2021-12-07

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Peng Zhou ,  Scott David Cohen ,  Gregg Darryl Wilensky

IPC: G06T7/13

Abstract: In implementations of object boundary generation, a computing device implements a boundary system to receive a mask defining a contour of an object depicted in a digital image, the mask having a lower resolution than the digital image. The boundary system maps a curve to the contour of the object and extracts strips of pixels from the digital image which are normal to points of the curve. A sample of the digital image is generated using the extracted strips of pixels which is input to a machine learning model. The machine learning model outputs a representation of a boundary of the object by processing the sample of the digital image.

公开(公告)号：US11244430B2

公开(公告)日：2022-02-08

申请号：US16830005

申请日：2020-03-25

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Yinan Zhao ,  Scott David Cohen

IPC: G06T5/00 ,  G06N3/04 ,  G06T7/33 ,  G06N3/08 ,  G06T3/00 ,  G06T11/40 ,  G06T5/50

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.

公开(公告)号：US20210295525A1

公开(公告)日：2021-09-23

申请号：US16822853

申请日：2020-03-18

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Peng Zhou ,  Scott David Cohen ,  Gregg Darryl Wilensky

IPC: G06T7/13

Abstract: In implementations of object boundary generation, a computing device implements a boundary system to receive a mask defining a contour of an object depicted in a digital image, the mask having a lower resolution than the digital image. The boundary system maps a curve to the contour of the object and extracts strips of pixels from the digital image which are normal to points of the curve. A sample of the digital image is generated using the extracted strips of pixels which is input to a machine learning model. The machine learning model outputs a representation of a boundary of the object by processing the sample of the digital image.

公开(公告)号：US20200226725A1

公开(公告)日：2020-07-16

申请号：US16830005

申请日：2020-03-25

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Yinan Zhao ,  Scott David Cohen

IPC: G06T5/00 ,  G06T5/50 ,  G06T11/40 ,  G06T7/33 ,  G06N3/08 ,  G06T3/00 ,  G06N3/04

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.

公开(公告)号：US10699388B2

公开(公告)日：2020-06-30

申请号：US15879354

申请日：2018-01-24

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Yinan Zhao ,  Scott David Cohen

IPC: G06T5/00 ,  G06T5/50 ,  G06T7/33 ,  G06T3/00 ,  G06N3/08 ,  G06N3/04 ,  G06T11/40

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.

公开(公告)号：US10657652B2

公开(公告)日：2020-05-19

申请号：US16359880

申请日：2019-03-20

Applicant: ADOBE INC.

Inventor： Brian Lynn Price ,  Stephen Schiller ,  Scott Cohen ,  Ning Xu

IPC: G06T7/194 ,  G06T7/90 ,  G06N3/08 ,  G06T7/11 ,  G06N3/04

Abstract: Methods and systems are provided for generating mattes for input images. A neural network system can be trained where the training includes training a first neural network that generates mattes for input images where the input images are synthetic composite images. Such a neural network system can further be trained where the training includes training a second neural network that generates refined mattes from the mattes produced by the first neural network. Such a trained neural network system can be used to input an image and trimap pair for which the trained system will output a matte. Such a matte can be used to extract an object from the input image. Upon extracting the object, a user can manipulate the object, for example, to composite the object onto a new background.

公开(公告)号：US20190228508A1

公开(公告)日：2019-07-25

申请号：US15879354

申请日：2018-01-24

Applicant: Adobe Inc.

Inventor： Brian Lynn Price ,  Yinan Zhao ,  Scott David Cohen

IPC: G06T5/00 ,  G06T5/50 ,  G06T11/40 ,  G06T7/33 ,  G06T3/00 ,  G06N3/08

Abstract: Fill techniques as implemented by a computing device are described to perform hole filling of a digital image. In one example, deeply learned features of a digital image using machine learning are used by a computing device as a basis to search a digital image repository to locate the guidance digital image. Once located, machine learning techniques are then used to align the guidance digital image with the hole to be filled in the digital image. Once aligned, the guidance digital image is then used to guide generation of fill for the hole in the digital image. Machine learning techniques are used to determine which parts of the guidance digital image are to be blended to fill the hole in the digital image and which parts of the hole are to receive new content that is synthesized by the computing device.