-
公开(公告)号：US09672866B2
公开(公告)日：2017-06-06
申请号：US14811265
申请日：2015-07-28
Applicant: Adobe Systems Incorporated
Inventor： Laura Sevilla-Lara , Elya Shechtman , Kalyan K. Sunkavalli
CPC classification number: G11B27/007 , G06K9/00744 , G06K9/342 , G06K9/40 , G06K9/6215 , H04N5/145 , H04N5/76 , H04N9/87
Abstract: Automated looping video creation techniques are described. In one or more implementations, a digital medium environment is configured to create a looping video that supports repeated playback that appears generally seamless to a user by one or more computing devices. Frames of a video are segmented into foreground and background regions by the one or more computing devices. Similarity of the foreground regions is determined of the segmented frames, one to another, by the one or more computing devices to use as a transition in the looping video. The looping video is synthesized as a subset of the video by the one or more computing devices as having the transition based on the determined similarity of first and second said frames.
-
公开(公告)号：US20170140514A1
公开(公告)日：2017-05-18
申请号：US14945308
申请日：2015-11-18
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Sohrab Amirghodsi , Elya Shechtman , Daniel Robert Goldman , Aliakbar Darabi
CPC classification number: G06T5/50 , G06T7/11 , G06T7/155 , G06T11/001 , G06T2200/24 , G06T2207/10024
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed at image synthesis utilizing an active mask. In one embodiment, input is received that identifies a target region within an image that is to be synthesized. A patch synthesis technique can then be performed to synthesize the target region based on portions of a source region that are identified by the patch synthesis technique. In embodiments, the patch synthesis technique includes, for at least one iteration, generating an active mask that indicates one or more portions of the target region as inactive. This active mask can be utilized by at least one process of the patch synthesis technique to ignore the one or more portions indicated as inactive by the active mask for the at least one iteration of the patch synthesis technique. Other embodiments may be described and/or claimed.
-
公开(公告)号：US09430715B1
公开(公告)日：2016-08-30
申请号：US14702588
申请日：2015-05-01
Applicant: Adobe Systems Incorporated
Inventor： Jue Wang , Kalyan Sunkavalli , Li-Qian Ma , Elya Shechtman
IPC: G06K9/34 , G06K9/46 , G06T5/00 , G06K9/42 , G06T7/00 , G06K9/40 , G06K9/44 , G06K9/62 , G06K9/66
CPC classification number: G06T7/0081 , G06K9/346 , G06T5/008 , G06T7/11 , G06T7/143 , G06T2207/10024 , G06T2207/20021 , G06T2207/20076 , G06T2207/20081
Abstract: Methods and systems for detection and removal of cast shadows from an image. In particular, one or more embodiments compute correspondences between image patches in the image using a grid-based patch-matching algorithm. One or more embodiments then train a regression model to detect shadows from the computed patch correspondences. One or more embodiments then segment the detected shadows into shadow regions and identify cast shadows from the shadow regions. Once the cast shadows are identified, one or more embodiments use patch-based synthesis of pixels guided by a direct inversion of the image. Optionally, one or more methods can use pixels from the synthesized image and the naïve inversion of the image, based on a synthesis confidence of each pixel, to produce a combined result.
Abstract translation: 用于从图像中检测和删除投影的方法和系统。 特别地，一个或多个实施例使用基于网格的补丁匹配算法来计算图像中的图像斑块之间的对应关系。 然后一个或多个实施例训练回归模型以从计算的补片对应度检测阴影。 然后，一个或多个实施例将检测到的阴影分割成阴影区域，并从阴影区域识别投射阴影。 一旦确定了投影，一个或多个实施例使用基于图像的直接反转引导的基于片段的合成像素。 可选地，一个或多个方法可以基于每个像素的合成置信度使用来自合成图像的像素和图像的初始反转，以产生组合结果。
-
公开(公告)号：US20150324985A1
公开(公告)日：2015-11-12
申请号：US14798285
申请日：2015-07-13
Applicant: Adobe Systems Incorporated
Inventor： Elya Shechtman , Jue Wang , Hyunjoon Lee , Seungyong Lee
CPC classification number: H04N5/23229 , G06T3/00 , G06T3/608 , G06T5/00 , G06T5/006 , G06T7/80 , G06T15/20
Abstract: Techniques and apparatus for automatic upright adjustment of digital images. An automatic upright adjustment technique is described that may provide an automated approach for straightening up slanted features in an input image to improve its perceptual quality. This correction may be referred to as upright adjustment. A set of criteria based on human perception may be used in the upright adjustment. A reprojection technique that implements an optimization framework is described that yields an optimal homography for adjustment based on the criteria and adjusts the image according to new camera parameters generated by the optimization. An optimization-based camera calibration technique is described that simultaneously estimates vanishing lines and points as well as camera parameters for an image; the calibration technique may, for example, be used to generate estimates of camera parameters and vanishing points and lines that are input to the reprojection technique.
Abstract translation: 用于数字图像自动竖直调整的技术和设备。 描述了自动立式调节技术，其可以提供用于矫正输入图像中的倾斜特征的自动化方法，以提高其感知质量。 这种校正可以被称为直立调节。 可以在直立式调整中使用基于人类感知的一组标准。 描述了实现优化框架的重投影技术，其基于标准产生用于调整的最佳单应性，并且根据由优化生成的新的相机参数来调整图像。 描述了基于优化的相机校准技术，其同时估计图像的消失线和点以及相机参数; 例如，校准技术可以用于生成输入到重投影技术的相机参数和消失点和线的估计。
-
公开(公告)号：US20150213583A1
公开(公告)日：2015-07-30
申请号：US14163910
申请日：2014-01-24
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Mohammad Rastegari , Aaron P. Hertzmann , Elya Shechtman
CPC classification number: G06T5/005 , G06T3/4015 , G06T3/4053 , G06T5/001 , G06T5/002 , G06T5/003 , G06T5/50 , G06T2207/20081 , G06T2207/20221
Abstract: An image prior as a shared basis mixture model is described. In one or more implementations, a plurality of image patches are generated from one or more images. A shared basis mixture model is learned to model an image patch distribution of the plurality of image patches from the one or more images as part of a Gaussian mixture model. An image may then be reconstructed using the shared basis mixture model as an image prior.
Abstract translation: 描述作为共享基础混合模型的图像。 在一个或多个实现中，从一个或多个图像生成多个图像块。 学习共享基础混合模型，以将来自一个或多个图像的多个图像块的图像补丁分布建模为高斯混合模型的一部分。 然后可以使用共享基础混合模型来重构图像作为图像。
-
Patent Agency Ranking
公开(公告)号：US09053392B2
公开(公告)日：2015-06-09
申请号：US14012770
申请日：2013-08-28
Applicant: Adobe Systems Incorporated
Inventor： Jianchao Yang , Guang Chen , Hailin Jin , Jonathan Brandt , Elya Shechtman
CPC classification number: G06K9/6267 , G06K9/00979 , G06K9/4671 , G06K9/6219 , G06K9/6298 , G06K9/6828
Abstract: A hierarchy machine may be configured as a clustering machine that utilizes local feature embedding to organize visual patterns into nodes that each represent one or more visual patterns. These nodes may be arranged as a hierarchy in which a node may have a parent-child relationship with one or more other nodes. The hierarchy machine may implement a node splitting and tree-learning algorithm that includes hard-splitting of nodes and soft-assignment of nodes to perform error-bounded splitting of nodes into clusters. This may enable the hierarchy machine, which may form all or part of a visual pattern recognition system, to perform large-scale visual pattern recognition, such as font recognition or facial recognition, based on a learned error-bounded tree of visual patterns.
Abstract translation: 层次机器可以被配置为利用局部特征嵌入将可视图案组织成每个表示一个或多个视觉图案的节点的聚类机器。 这些节点可以被布置为其中节点可以与一个或多个其他节点具有父子关系的层级。 层次机器可以实现节点分割和树学习算法，其包括节点的硬分割和节点的软分配，以执行节点到分簇的有界限制的分割。 这可以使得可以形成视觉图案识别系统的全部或一部分的层次机器基于学习的有界错误的视觉图案树来执行诸如字体识别或面部识别的大规模视觉模式识别。
-
公开(公告)号：US20140333644A1
公开(公告)日：2014-11-13
申请号：US14339161
申请日：2014-07-23
Applicant: Adobe Systems Incorporated
Inventor： Dan Goldman , Elya Shechtman
CPC classification number: G06T1/60 , G06T5/005 , G06T2207/20021 , G06T2207/20172
Abstract: A first image at a first resolution is received, the first image having a first hole therein. Based on the first image, a second image is generated at a second resolution lower than the first resolution, the second image having a second hole therein corresponding to the first hole. In the second image, one or more second-image source patches for the second hole are identified. At least one first-image source patch in the first image is identified based on a location of the identified second-image source patch. The identified at least one first-image source patch are stored in memory. Fill content are identified in the at least one first-image source patch stored in the memory. The identified fill content are placed in the first hole.
Abstract translation: 接收第一分辨率的第一图像，第一图像在其中具有第一孔。 基于第一图像，以比第一分辨率低的第二分辨率产生第二图像，第二图像在其中具有与第一孔相对应的第二孔。 在第二图像中，识别用于第二孔的一个或多个第二图像源补丁。 基于所识别的第二图像源补丁的位置来识别第一图像中的至少一个第一图像源补丁。 所识别的至少一个第一图像源补丁存储在存储器中。 填充内容在存储在存储器中的至少一个第一图像源补丁中被识别。 所识别的填充内容被放置在第一个孔中。
-
公开(公告)号：US20130286221A1
公开(公告)日：2013-10-31
申请号：US13871597
申请日：2013-04-26
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Elya Shechtman , Jue Wang , Hyunjoon Lee , Seungyong Lee
CPC classification number: H04N5/23229 , G06T3/00 , G06T3/608 , G06T5/00 , G06T5/006 , G06T7/80 , G06T15/20
Abstract: Techniques and apparatus for automatic upright adjustment of digital images. An automatic upright adjustment technique is described that may provide an automated approach for straightening up slanted features in an input image to improve its perceptual quality. This correction may be referred to as upright adjustment. A set of criteria based on human perception may be used in the upright adjustment. A reprojection technique that implements an optimization framework is described that yields an optimal homography for adjustment based on the criteria and adjusts the image according to new camera parameters generated by the optimization. An optimization-based camera calibration technique is described that simultaneously estimates vanishing lines and points as well as camera parameters for an image; the calibration technique may, for example, be used to generate estimates of camera parameters and vanishing points and lines that are input to the reprojection technique.
-
公开(公告)号：US20190042875A1
公开(公告)日：2019-02-07
申请号：US16148166
申请日：2018-10-01
Applicant: Adobe Systems Incorporated
Inventor： Nathan Carr , Kalyan Sunkavalli , Michal Lukac , Elya Shechtman
IPC: G06K9/62
Abstract: The present disclosure is directed toward systems and methods for image patch matching. In particular, the systems and methods described herein sample image patches to identify those image patches that match a target image patch. The systems and methods described herein probabilistically accept image patch proposals as potential matches based on an oracle. The oracle is computationally inexpensive to evaluate but more approximate than similarity heuristics. The systems and methods use the oracle to quickly guide the search to areas of the search space more likely to have a match. Once areas are identified that likely include a match, the systems and methods use a more accurate similarity function to identify patch matches.
-
公开(公告)号：US10074033B2
公开(公告)日：2018-09-11
申请号：US15286905
申请日：2016-10-06
Applicant: Adobe Systems Incorporated
Inventor： Nathan Carr , Kalyan Sunkavalli , Michal Lukac , Elya Shechtman
CPC classification number: G06K9/621 , G06K9/38 , G06K2009/6213 , G06T7/337
Abstract: Certain embodiments involve using labels to track high-frequency offsets for patch-matching. For example, a processor identifies an offset between a first source image patch and a first target image patch. If the first source image patch and the first target image patch are sufficiently similar, the processor updates a data structure to include a label specifying the offset. The processor associates, via the data structure, the first source image patch with the label. The processor subsequently selects certain high-frequency offsets, including the identified offset, from frequently occurring offsets in the data structure. The processor uses these offsets to identify a second target image patch, which is located at the identified offset from a second source image patch. The processor associates, via the data structure, the second source image patch with the identified offset based on a sufficient similarity between the second source image patch and the second target image patch.
-
-
-
-
-
-
-
-
-
Search Results
73
records
(took 0.03 seconds)
