公开(公告)号：US10410351B2

公开(公告)日：2019-09-10

申请号：US16116609

申请日：2018-08-29

Applicant: Adobe Inc.

Inventor： Zhe Lin ,  Xin Lu ,  Xiaohui Shen ,  Jimei Yang ,  Chenxi Liu

IPC: G06K9/00 ,  G06T7/11 ,  G06F17/27 ,  G10L15/26

Abstract: The invention is directed towards segmenting images based on natural language phrases. An image and an n-gram, including a sequence of tokens, are received. An encoding of image features and a sequence of token vectors are generated. A fully convolutional neural network identifies and encodes the image features. A word embedding model generates the token vectors. A recurrent neural network (RNN) iteratively updates a segmentation map based on combinations of the image feature encoding and the token vectors. The segmentation map identifies which pixels are included in an image region referenced by the n-gram. A segmented image is generated based on the segmentation map. The RNN may be a convolutional multimodal RNN. A separate RNN, such as a long short-term memory network, may iteratively update an encoding of semantic features based on the order of tokens. The first RNN may update the segmentation map based on the semantic feature encoding.

公开(公告)号：US10460214B2

公开(公告)日：2019-10-29

申请号：US15799395

申请日：2017-10-31

Applicant: Adobe Inc.

Inventor： Xin Lu ,  Zhe Lin ,  Xiaohui Shen ,  Jimei Yang ,  Jianming Zhang ,  Jen-Chan Jeff Chien ,  Chenxi Liu

IPC: G06K9/66 ,  G06K9/46 ,  G06T7/194

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for segmenting objects in digital visual media utilizing one or more salient content neural networks. In particular, in one or more embodiments, the disclosed systems and methods train one or more salient content neural networks to efficiently identify foreground pixels in digital visual media. Moreover, in one or more embodiments, the disclosed systems and methods provide a trained salient content neural network to a mobile device, allowing the mobile device to directly select salient objects in digital visual media utilizing a trained neural network. Furthermore, in one or more embodiments, the disclosed systems and methods train and provide multiple salient content neural networks, such that mobile devices can identify objects in real-time digital visual media feeds (utilizing a first salient content neural network) and identify objects in static digital images (utilizing a second salient content neural network).

公开(公告)号：US20190130229A1

公开(公告)日：2019-05-02

申请号：US15799395

申请日：2017-10-31

Applicant: Adobe Inc.

Inventor： Xin Lu ,  Zhe Lin ,  Xiaohui Shen ,  Jimei Yang ,  Jianming Zhang ,  Jen-Chan Jeff Chien ,  Chenxi Liu

IPC: G06K9/66 ,  G06K9/46 ,  G06T7/194

CPC classification number: G06K9/66 ,  G06K9/4628 ,  G06K9/4671 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/194 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for segmenting objects in digital visual media utilizing one or more salient content neural networks. In particular, in one or more embodiments, the disclosed systems and methods train one or more salient content neural networks to efficiently identify foreground pixels in digital visual media. Moreover, in one or more embodiments, the disclosed systems and methods provide a trained salient content neural network to a mobile device, allowing the mobile device to directly select salient objects in digital visual media utilizing a trained neural network. Furthermore, in one or more embodiments, the disclosed systems and methods train and provide multiple salient content neural networks, such that mobile devices can identify objects in real-time digital visual media feeds (utilizing a first salient content neural network) and identify objects in static digital images (utilizing a second salient content neural network).

公开(公告)号：US11941746B2

公开(公告)日：2024-03-26

申请号：US17466670

申请日：2021-09-03

Applicant: Adobe Inc.

Inventor： Aaron Hertzmann ,  Shayan Hoshyari ,  Chenxi Liu

IPC: G06T15/20 ,  G06T7/564 ,  G06T17/20

CPC classification number: G06T15/20 ,  G06T7/564 ,  G06T17/205

Abstract: Embodiments are disclosed for computing accurate smooth occluding contours. In one embodiment, a method of computing accurate smooth occluding contours includes projecting a boundary polygon associated with a first region of a three-dimensional (3D) object to a two-dimensional (2D) image plane, the boundary polygon comprising a plurality of contour vertices and edges connecting the plurality of contour vertices, triangulating the first region in the 2D image plane to generate a 2D triangulation, and generating a 3D mesh for the first region by mapping the 2D triangulation to the 3D object.