-
公开(公告)号：US20140169684A1
公开(公告)日：2014-06-19
申请号：US13713729
申请日：2012-12-13
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Kevin Armin Samii , Zhe Lin , Radomir Mech
IPC: G06K9/62
CPC classification number: G06K9/6202 , G06K9/48 , G06K9/6215
Abstract: Systems and methods are provided for generating a distance metric. An image manipulation application receives first and second input images. The image manipulation application generates first and second sets of points corresponding to respective edges of a first object in the first input image and a second object in the second input image. The image manipulation application determines costs of arcs connecting each point from the first set to each point of the second set based on point descriptors for each point of each arc. The image manipulation application determines a minimum set of costs between the first set and the second set that includes a cost of each arc connecting each point of the second set to a point in the first set. The image manipulation application obtains, based at least in part on the minimum set of costs, a distance metric for first and second input images.
Abstract translation: 提供了用于产生距离度量的系统和方法。 图像处理应用接收第一和第二输入图像。 图像处理应用产生与第一输入图像中的第一对象的相应边缘相对应的第一和第二组点，以及第二输入图像中的第二对象。 图像处理应用程序确定基于每个弧的每个点的点描述符将每个点从第一组连接到第二组的每个点的弧的成本。 图像处理应用程序确定第一组和第二组之间的最小成本集合，其包括将第二组的每个点连接到第一组中的点的每个弧的成本。 图像处理应用至少部分地基于最小成本集获得第一和第二输入图像的距离度量。
-
公开(公告)号：US20190108640A1
公开(公告)日：2019-04-11
申请号：US15730564
申请日：2017-10-11
Applicant: Adobe Systems Incorporated
Inventor： Jianming Zhang , Zijun Wei , Zhe Lin , Xiaohui Shen , Radomir Mech
Abstract: Various embodiments describe using a neural network to evaluate image crops in substantially real-time. In an example, a computer system performs unsupervised training of a first neural network based on unannotated image crops, followed by a supervised training of the first neural network based on annotated image crops. Once this first neural network is trained, the computer system inputs image crops generated from images to this trained network and receives composition scores therefrom. The computer system performs supervised training of a second neural network based on the images and the composition scores.
-
公开(公告)号：US10198590B2
公开(公告)日：2019-02-05
申请号：US14938724
申请日：2015-11-11
Applicant: Adobe Systems Incorporated
Inventor： Zeke Koch , Gavin Stuart Peter Miller , Jonathan W. Brandt , Nathan A. Carr , Radomir Mech , Walter Wei-Tuh Chang , Scott D. Cohen , Hailin Jin
IPC: G06F21/62 , G06F3/0484 , G06F17/30
Abstract: Content creation collection and navigation techniques and systems are described. In one example, a representative image is used by a content sharing service to interact with a collection of images provided as part of a search result. In another example, a user interface image navigation control is configured to support user navigation through images based on one or more metrics. In a further example, a user interface image navigation control is configured to support user navigation through images based on one or more metrics identified for an object selected from the image. In yet another example, collections of images are leveraged as part of content creation. In another example, data obtained from a content sharing service is leveraged to indicate suitability of images of a user for licensing as part of the service.
-
公开(公告)号：US20180357803A1
公开(公告)日：2018-12-13
申请号：US15620636
申请日：2017-06-12
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Jianming Zhang , Zhe Lin , Radomir Mech , Xiaohui Shen
CPC classification number: G06T11/60 , G06T3/40 , G06T7/11 , G06T2210/22
Abstract: Embodiments of the present invention are directed to facilitating region of interest preservation. In accordance with some embodiments of the present invention, a region of interest preservation score using adaptive margins is determined. The region of interest preservation score indicates an extent to which at least one region of interest is preserved in a candidate image crop associated with an image. A region of interest positioning score is determined that indicates an extent to which a position of the at least one region of interest is preserved in the candidate image crop associated with the image. The region of interest preservation score and/or the preserving score are used to select a set of one or more candidate image crops as image crop suggestions.
-
公开(公告)号：US20180268535A1
公开(公告)日：2018-09-20
申请号：US15981166
申请日：2018-05-16
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Zhe Lin , Shu Kong , Radomir Mech
CPC classification number: G06T7/0002 , G06K9/623 , G06K9/6256 , G06N3/0454 , G06N3/08 , G06T2207/20081 , G06T2207/30168
Abstract: Systems and methods are disclosed for estimating aesthetic quality of digital images using deep learning. In particular, the disclosed systems and methods describe training a neural network to generate an aesthetic quality score digital images. In particular, the neural network includes a training structure that compares relative rankings of pairs of training images to accurately predict a relative ranking of a digital image. Additionally, in training the neural network, an image rating system can utilize content-aware and user-aware sampling techniques to identify pairs of training images that have similar content and/or that have been rated by the same or different users. Using content-aware and user-aware sampling techniques, the neural network can be trained to accurately predict aesthetic quality ratings that reflect subjective opinions of most users as well as provide aesthetic scores for digital images that represent the wide spectrum of aesthetic preferences of various users.
-
Patent Agency Ranking
公开(公告)号：US10062215B2
公开(公告)日：2018-08-28
申请号：US15014386
申请日：2016-02-03
Applicant: Adobe Systems Incorporated
Inventor： Radomir Mech , Mehmet Ersin Yumer , Haibin Huang
CPC classification number: G06T19/20 , G06T11/001 , G06T17/00 , G06T2219/2021
Abstract: Methods and systems are directed to improving the convenience of drawing applications. Some examples include generating 3D drawing objects using a drawing application and selecting one based on a 2D design (in some cases a hand-drawn sketch) provided by a user. The user provided 2D design is separated into an outline perimeter and interior design, and corresponding vectors are then generated. These vectors are then used with analogous vectors generated for drawing objects. The selection of a drawing object to correspond to the 2D design is based on finding a drawing object having a minimum difference between its vectors and the vectors of the 2D design. The selected drawing object is then used to generate a drawing object configured to receive edits from the user. This reduces the inconvenience required to manually reproduce the 2D design in the drawing application.
-
公开(公告)号：US10002415B2
公开(公告)日：2018-06-19
申请号：US15097113
申请日：2016-04-12
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Zhe Lin , Shu Kong , Radomir Mech
CPC classification number: G06T7/0002 , G06K9/623 , G06K9/6256 , G06N3/0454 , G06N3/08 , G06T2207/20081 , G06T2207/30168
Abstract: Systems and methods are disclosed for estimating aesthetic quality of digital images using deep learning. In particular, the disclosed systems and methods describe training a neural network to generate an aesthetic quality score digital images. In particular, the neural network includes a training structure that compares relative rankings of pairs of training images to accurately predict a relative ranking of a digital image. Additionally, in training the neural network, an image rating system can utilize content-aware and user-aware sampling techniques to identify pairs of training images that have similar content and/or that have been rated by the same or different users. Using content-aware and user-aware sampling techniques, the neural network can be trained to accurately predict aesthetic quality ratings that reflect subjective opinions of most users as well as provide aesthetic scores for digital images that represent the wide spectrum of aesthetic preferences of various users.
-
公开(公告)号：US09817847B2
公开(公告)日：2017-11-14
申请号：US15470473
申请日：2017-03-27
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Xin Lu , Zhe Lin , Radomir Mech
CPC classification number: G06F17/30256 , G06F17/30247 , G06F17/30271 , G06K9/00221 , G06K9/00261 , G06K9/036 , G06K9/4628 , G06K9/6215 , G06K9/6227 , G06K9/6272 , G06K9/66 , G06N3/04 , G06N3/08
Abstract: Neural network image curation techniques are described. In one or more implementations, curation is controlled of images that represent a repository of images. A plurality of images of the repository are curated by one or more computing devices to select representative images of the repository. The curation includes calculating a score based on image and face aesthetics, jointly, for each of the plurality of images through processing by a neural network, ranking the plurality of images based on respective said scores, and selecting one or more of the plurality of images as one of the representative images of the repository based on the ranking and a determination that the one or more said images are not visually similar to images that have already been selected as one of the representative images of the repository.
-
公开(公告)号：US20170212661A1
公开(公告)日：2017-07-27
申请号：US15005927
申请日：2016-01-25
Applicant: Adobe Systems Incorporated
Inventor： Daichi Ito , Radomir Mech , Nathan A. Carr , Tsukasa Fukusato
IPC: G06F3/0481 , G06F3/0482 , G06T19/20 , G06F3/0484 , G06T15/20 , G06T17/20
CPC classification number: G06F3/04815 , G06F3/0482 , G06F3/04845 , G06T15/20 , G06T17/20 , G06T19/20 , G06T2200/04
Abstract: Techniques and systems are described to generate a three-dimensional model from two-dimensional images. A plurality of inputs is received, formed through user interaction with a user interface. Each of the plurality of inputs define a respective user-specified point on the object in a respective one of the plurality of images. A plurality of estimated points on the object are generated automatically and without user intervention. Each of the plurality of estimated points corresponds to a respective user-specified point for other ones of the plurality of images. The plurality of estimated points is displayed for the other ones of the plurality of images in the user interface by a computing device. A mesh of the three-dimensional model of the object is generated by the computing device by mapping respective ones of the user-specified points to respective ones of the estimated points in the plurality of images.
-
公开(公告)号：US20170199898A1
公开(公告)日：2017-07-13
申请号：US15470473
申请日：2017-03-27
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Xin Lu , Zhe Lin , Radomir Mech
CPC classification number: G06F17/30256 , G06F17/30247 , G06F17/30271 , G06K9/00221 , G06K9/00261 , G06K9/036 , G06K9/4628 , G06K9/6215 , G06K9/6227 , G06K9/6272 , G06K9/66 , G06N3/04 , G06N3/08
Abstract: Neural network image curation techniques are described. In one or more implementations, curation is controlled of images that represent a repository of images. A plurality of images of the repository are curated by one or more computing devices to select representative images of the repository. The curation includes calculating a score based on image and face aesthetics, jointly, for each of the plurality of images through processing by a neural network, ranking the plurality of images based on respective said scores, and selecting one or more of the plurality of images as one of the representative images of the repository based on the ranking and a determination that the one or more said images are not visually similar to images that have already been selected as one of the representative images of the repository.
-
-
-
-
-
-
-
-
-
Search Results
66
records
(took 0.028 seconds)
