-
公开(公告)号：US20170132526A1
公开(公告)日：2017-05-11
申请号：US14978350
申请日：2015-12-22
Applicant: Adobe Systems Incorporated
Inventor： Scott D. Cohen , Walter Wei-Tuh Chang , Brian L. Price , Mohamed Hamdy Mahmoud Abdelbaky Elhoseiny
CPC classification number: G06F17/2785 , G06N3/0454 , G06N5/022
Abstract: Techniques and systems are described to model and extract knowledge from images. A digital medium environment is configured to learn and use a model to compute a descriptive summarization of an input image automatically and without user intervention. Training data is obtained to train a model using machine learning in order to generate a structured image representation that serves as the descriptive summarization of an input image. The images and associated text are processed to extract structured semantic knowledge from the text, which is then associated with the images. The structured semantic knowledge is processed along with corresponding images to train a model using machine learning such that the model describes a relationship between text features within the structured semantic knowledge. Once the model is learned, the model is usable to process input images to generate a structured image representation of the image.
-
公开(公告)号：US20170053412A1
公开(公告)日：2017-02-23
申请号：US14832328
申请日：2015-08-21
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Zhe Lin , Scott D. Cohen , Brian L. Price
CPC classification number: G06T7/536 , G06K9/6264
Abstract: Image depth inference techniques and systems from semantic labels are described. In one or more implementations, a digital medium environment includes one or more computing devices to control a determination of depth within an image. Regions of the image are semantically labeled by the one or more computing devices. At least one of the semantically labeled regions is decomposed into a plurality of segments formed as planes generally perpendicular to a ground plane of the image. Depth of one or more of the plurality of segments is then inferred based on relationships of respective segments with respective locations of the ground plane of the image. A depth map is formed that describes depth for the at least one semantically labeled region based at least in part on the inferred depths for the one or more of the plurality of segments.
Abstract translation: 描述了来自语义标签的图像深度推理技术和系统。 在一个或多个实现中，数字媒体环境包括用于控制图像内的深度的确定的一个或多个计算设备。 图像的区域被一个或多个计算设备语义地标记。 至少一个语义标记的区域被分解成多个段，其形成为大致垂直于图像的接地平面的平面。 然后基于各个段与图像的接地平面的相应位置的关系来推断多个段中的一个或多个段的深度。 形成深度图，其至少部分地基于所述多个段中的一个或多个段的推断深度来描述所述至少一个语义标记区域的深度。
-
公开(公告)号：US20160191753A1
公开(公告)日：2016-06-30
申请号：US15063240
申请日：2016-03-07
Applicant: Adobe Systems Incorporated
Inventor： Hailin Jin , Zhuoyuan Chen , Scott D. Cohen , Jianchao Yang , Zhe Lin
CPC classification number: H04N5/21 , G06T3/4053 , G06T3/4076 , G06T5/002 , G06T5/003 , G06T5/20 , G06T5/50 , G06T7/269 , G06T2207/10016 , G06T2207/20021 , G06T2207/20032 , G06T2207/20182 , G06T2207/20201 , H04N5/144 , H04N5/145 , H04N5/147
Abstract: In techniques for video denoising using optical flow, image frames of video content include noise that corrupts the video content. A reference frame is selected, and matching patches to an image patch in the reference frame are determined from within the reference frame. A noise estimate is computed for previous and subsequent image frames relative to the reference frame. The noise estimate for an image frame is computed based on optical flow, and is usable to determine a contribution of similar motion patches to denoise the image patch in the reference frame. The similar motion patches from the previous and subsequent image frames that correspond to the image patch in the reference frame are determined based on the optical flow computations. The image patch is denoised based on an average of the matching patches from reference frame and the similar motion patches determined from the previous and subsequent image frames.
Abstract translation: 在使用光流的视频去噪的技术中，视频内容的图像帧包括破坏视频内容的噪声。 选择参考帧，并且从参考帧内确定参考帧中的图像块的匹配补丁。 针对相对于参考帧的先前和后续图像帧计算噪声估计。 基于光流计算图像帧的噪声估计，并且可用于确定类似运动补丁对参考帧中的图像补丁进行去噪的贡献。 基于光流计算确定与参考帧中的图像块相对应的来自先前和后续图像帧的类似运动补丁。 基于来自参考帧的匹配补丁的平均值和从先前和后续图像帧确定的类似运动补丁，去除图像补丁。
-
公开(公告)号：US09380286B2
公开(公告)日：2016-06-28
申请号：US13866632
申请日：2013-04-19
Applicant: Adobe Systems Incorporated
Inventor： Scott D. Cohen , Brian L. Price , Bryan Stuart Morse , Joel A. Howard
IPC: H04N13/00
CPC classification number: H04N13/111
Abstract: Stereoscopic target region filling techniques are described. Techniques are described in which stereo consistency is promoted between target regions, such as by sharing information during computation. Techniques are also described in which target regions of respective disparity maps are completed to promote consistency between the disparity maps. This estimated disparity may then be used as a guide to completion of a missing texture in the target region. Techniques are further described in which cross-image searching and matching is employed by leveraging a plurality of images. This may including giving preference to matches with cross-image consistency to promote consistency, thereby enforcing stereo consistency between stereo images when applicable.
Abstract translation: 描述了立体目标区填充技术。 描述了在目标区域之间促进立体一致性的技术，例如通过在计算期间共享信息。 还描述了其中完成各个视差图的目标区域以促进视差图之间的一致性的技术。 然后可以将该估计的差异用作在目标区域中完成缺失纹理的指导。 进一步描述了通过利用多个图像来采用跨图像搜索和匹配的技术。 这可能包括优先考虑与跨图像一致性的匹配以促进一致性，从而在适用时实现立体图像之间的立体一致性。
-
公开(公告)号：US09165373B2
公开(公告)日：2015-10-20
申请号：US13794219
申请日：2013-03-11
Applicant: Adobe Systems Incorporated
Inventor： Hailin Jin , Zhuoyuan Chen , Zhe Lin , Scott D. Cohen
CPC classification number: G06T7/2013 , G06T7/215 , G06T7/223 , G06T7/248
Abstract: In embodiments of statistics of nearest neighbor fields, matching patches of a nearest neighbor field can be determined at image grid locations of a first digital image and a second digital image. A motion field can then be determined based on motion data of the matching patches. Predominant motion components of the motion field can be determined based on statistics of the motion data to generate a final motion field. The predominant motion components correspond to a motion of objects as represented by a displacement between the first and second digital images. One of the predominant motion components can then be assigned to each of the matching patches to optimize the final motion field of the matching patches.
Abstract translation: 在最近邻域的统计的实施例中，可以在第一数字图像和第二数字图像的图像网格位置处确定最近邻域的匹配块。 然后可以基于匹配补丁的运动数据来确定运动场。 可以基于运动数据的统计来确定运动场的主要运动分量以产生最终运动场。 主要运动分量对应于由第一和第二数字图像之间的位移表示的物体的运动。 然后可以将主要运动分量中的一个分配给每个匹配补丁以优化匹配补丁的最终运动场。
-
Patent Agency Ranking
公开(公告)号：US09129399B2
公开(公告)日：2015-09-08
申请号：US13794300
申请日：2013-03-11
Applicant: Adobe Systems Incorporated
Inventor： Hailin Jin , Zhuoyuan Chen , Zhe Lin , Scott D. Cohen
CPC classification number: G06T7/204 , G06T7/215 , G06T7/223 , G06T7/248 , G06T7/337 , G06T2207/20016 , G06T2207/20021
Abstract: In embodiments of optical flow with nearest neighbor field fusion, an initial motion field can be generated based on the apparent motion of objects between digital images, and the initial motion field accounts for small displacements of the object motion. Matching patches of a nearest neighbor field can also be determined for the digital images, where patches of an initial size are compared to determine the matching patches, and the nearest neighbor field accounts for large displacements of the object motion. Additionally, region patch matches can be compared and determined between the digital images, where the region patches are larger than the initial size matching patches. Optimal pixel assignments can then be determined for a fused image representation of the digital images, where the optimal pixel assignments are determined from the initial motion field, the matching patches, and the region patch matches.
Abstract translation: 在具有最近邻场融合的光流的实施例中，可以基于数字图像之间的物体的明显运动来生成初始运动场，并且初始运动场考虑到物体运动的小位移。 还可以为数字图像确定最近邻域的匹配补丁，其中比较初始大小的补丁以确定匹配补丁，并且最近邻域考虑对象运动的大位移。 另外，可以在数字图像之间比较和确定区域补丁匹配，其中区域补丁大于初始大小匹配补丁。 然后可以确定数字图像的融合图像表示的最佳像素分配，其中从初始运动场，匹配补丁和区域补丁匹配确定最佳像素分配。
-
公开(公告)号：US20140368509A1
公开(公告)日：2014-12-18
申请号：US13920957
申请日：2013-06-18
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jianchao Yang , Scott D. Cohen
IPC: G06T3/40
CPC classification number: G06T3/40 , G06T3/4053 , G06T3/4076 , G06T5/002 , G06T5/003 , G06T2207/20012 , G09G2340/0407
Abstract: Image upscaling techniques are described. These techniques may include use of iterative and adjustment upscaling techniques to upscale an input image. A variety of functionality may be incorporated as part of these techniques, examples of which include content-adaptive patch finding techniques that may be employed to give preference to an in-place patch to minimize structure distortion. In another example, content metric techniques may be employed to assign weights for combining patches. In a further example, algorithm parameters may be adapted with respect to algorithm iterations, which may be performed to increase efficiency of computing device resource utilization and speed of performance. For instance, algorithm parameters may be adapted to enforce a minimum and/or maximum number to iterations, cease iterations for image sizes over a threshold amount, set sampling step sizes for patches, employ techniques based on color channels (which may include independence and joint processing techniques), and so on.
Abstract translation: 描述了图像升高技术。 这些技术可以包括使用迭代和调整放大技术来升高输入图像。 作为这些技术的一部分，可以并入各种功能，其示例包括可用于优先使用就地补丁以最小化结构失真的内容自适应补片发现技术。 在另一示例中，可以采用内容度量技术来分配用于组合补丁的权重。 在另一示例中，算法参数可以针对算法迭代进行调整，这可以被执行以提高计算设备资源利用率和性能的效率。 例如，算法参数可以适于对迭代执行最小和/或最大数量，停止针对阈值量的图像大小的迭代，设置用于补丁的采样步长，采用基于颜色通道的技术（其可以包括独立性和联合 处理技术）等。
-
公开(公告)号：US20140254882A1
公开(公告)日：2014-09-11
申请号：US13794300
申请日：2013-03-11
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Hailin Jin , Zhuoyuan Chen , Zhe Lin , Scott D. Cohen
IPC: G06K9/46
CPC classification number: G06T7/204 , G06T7/215 , G06T7/223 , G06T7/248 , G06T7/337 , G06T2207/20016 , G06T2207/20021
Abstract: In embodiments of optical flow with nearest neighbor field fusion, an initial motion field can be generated based on the apparent motion of objects between digital images, and the initial motion field accounts for small displacements of the object motion. Matching patches of a nearest neighbor field can also be determined for the digital images, where patches of an initial size are compared to determine the matching patches, and the nearest neighbor field accounts for large displacements of the object motion. Additionally, region patch matches can be compared and determined between the digital images, where the region patches are larger than the initial size matching patches. Optimal pixel assignments can then be determined for a fused image representation of the digital images, where the optimal pixel assignments are determined from the initial motion field, the matching patches, and the region patch matches.
Abstract translation: 在具有最近邻场融合的光流的实施例中，可以基于数字图像之间的物体的明显运动来生成初始运动场，并且初始运动场考虑到物体运动的小位移。 还可以为数字图像确定最近邻域的匹配补丁，其中比较初始大小的补丁以确定匹配补丁，并且最近邻域考虑对象运动的大位移。 另外，可以在数字图像之间比较和确定区域补丁匹配，其中区域补丁大于初始大小匹配补丁。 然后可以确定数字图像的融合图像表示的最佳像素分配，其中从初始运动场，匹配补丁和区域补丁匹配确定最佳像素分配。
-
公开(公告)号：US08818082B2
公开(公告)日：2014-08-26
申请号：US13958044
申请日：2013-08-02
Applicant: Adobe Systems Incorporated
Inventor： Stephen N. Schiller , Scott D. Cohen , Jingnan Wang
CPC classification number: G06T11/60 , G06K9/209 , G06K9/40 , G06K9/4647 , G06K9/6278
Abstract: A blur classification module may compute the probability that a given pixel in a digital image was blurred using a given two-dimensional blur kernel, and may store the computed probability in a blur classification probability matrix that stores probability values for all combinations of image pixels and the blur kernels in a set of likely blur kernels. Computing these probabilities may include computing a frequency power spectrum for windows into the digital image and/or for the likely blur kernels. The blur classification module may generate a coherent mapping between pixels of the digital image and respective blur states, and/or may perform a segmentation of the image into blurry and sharp regions, dependent on values stored in the matrix. Input image data may be pre-processed. Blur classification results may be employed in image editing operations to automatically target image subjects or background regions, or to estimate the depth of image elements.
Abstract translation: 模糊分类模块可以使用给定的二维模糊核心来计算数字图像中的给定像素模糊的概率，并且可以将所计算的概率存储在模糊分类概率矩阵中，所述模糊分类概率矩阵存储图像像素的所有组合的概率值， 一组可能的模糊内核中的模糊内核。 计算这些概率可以包括计算窗口进入数字图像和/或可能的模糊内核的频率功率谱。 模糊分类模块可以产生数字图像的像素和相应的模糊状态之间的相干映射，和/或可以根据存储在矩阵中的值，将图像分割成模糊和清晰的区域。 可以预处理输入图像数据。 可以在图像编辑操作中使用模糊分类结果来自动对象图像对象或背景区域，或者估计图像元素的深度。
-
公开(公告)号：US20180286023A1
公开(公告)日：2018-10-04
申请号：US15474459
申请日：2017-03-30
Applicant: Adobe Systems Incorporated
Inventor： Zhe Zhu , Scott D. Cohen , Brian L. Price
IPC: G06T5/20
CPC classification number: G06T5/20 , G06T5/005 , G06T5/50 , G06T7/11 , G06T2207/20048
Abstract: Techniques and systems are described to support digital image processing through use of an image repository, e.g., a stock image database or other storage. In one example, a plurality of candidate digital images are obtained from an image repository based on a target digital image. A plurality of transformations are generated to be applied to the target digital image, each transformation based on a respective candidate digital image. Semantic information is employed as part of the transformations, e.g., blending, filtering, or alignment. A plurality of transformed target digital images are generated based at least in part through application of the plurality of transformations to the target image.
-
-
-
-
-
-
-
-
-
Search Results
54
records
(took 0.024 seconds)
