-
公开(公告)号：US20150036943A1
公开(公告)日：2015-02-05
申请号：US13954112
申请日：2013-07-30
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin
IPC: G06T5/00
CPC classification number: G06T5/003 , G06T3/4053 , G06T5/50 , G06T2207/20012 , G06T2207/20182
Abstract: Techniques for sharpening an image using local spatial adaptation and/or patch-based image processing. An image can be sharpened by creating a high-frequency image and then combining that high frequency image with the image. This process can be applied iteratively by using the output of one iteration, i.e., the sharpened image, as the input to the next iteration. Using local spatial adaptation and/or patch-based techniques can provide various advantages. How to change the intensity at a given position in the image can be calculated from more than just information about that same position in the input image and the blurred image. By using information about neighboring positions an improved high frequency image can be determined that, when combined with the input image, reduces ringing and halo artifacts, suppresses noise boosting, and/or generates results with sharper and cleaner edges and details.
Abstract translation: 使用局部空间适应和/或基于补丁的图像处理锐化图像的技术。 通过创建高频图像，然后将高频图像与图像组合，可以对图像进行锐化。 该过程可以通过使用一次迭代的输出（即，锐化的图像）作为下一次迭代的输入来迭代地应用。 使用局部空间适应和/或补丁技术可以提供各种优点。 如何改变图像中给定位置的强度可以从不仅仅是关于输入图像和模糊图像中相同位置的信息来计算。 通过使用关于相邻位置的信息，可以确定改进的高频图像，当与输入图像组合时，减少振铃和晕圈伪影，抑制噪声提升，和/或产生具有更清晰和更清晰的边缘和细节的结果。
-
公开(公告)号：US20140355959A1
公开(公告)日：2014-12-04
申请号：US13904903
申请日：2013-05-29
Applicant: Adobe Systems Incorporated
Inventor： Haili Jin , Scott David Cohen , Zhe Lin
IPC: G11B27/031 , G06T7/20
CPC classification number: G06T5/002 , G06T5/003 , G06T5/009 , G06T7/20 , G06T7/248 , G06T2207/10016 , G11B27/031 , H04N19/51
Abstract: A method and systems of identifying one or more patches in three or more frames in a video are provided. A region in a reference frame of the video may be detected. A set of regions in a prior frame and subsequent frame that are similar to the region in the reference frame may then be identified. Temporal consistency between the region in the reference frame and two or more regions in the set of regions in the prior and subsequent frames may then be calculated. Patches of regions in the first, reference, and third frames may be identified based at least in part on the calculated temporal consistencies, with each patch identifying a region in the reference frame that can be mapped to a similar region in the prior and subsequent frames.
Abstract translation: 提供了识别视频中的三个或更多个帧中的一个或多个补丁的方法和系统。 可以检测视频的参考帧中的区域。 然后可以识别与参考帧中的区域相似的先前帧和后续帧中的一组区域。 然后可以计算参考帧中的区域与先前帧和后续帧中的区域集合中的两个或更多个区域之间的时间一致性。 可以至少部分地基于所计算的时间一致性来识别第一，参考和第三帧中的区域的补丁，每个补丁标识参考帧中可以映射到先前和后续帧中的相似区域的区域 。
-
公开(公告)号：US20140254933A1
公开(公告)日：2014-09-11
申请号：US13794125
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: G06K9/4642 , G06T7/238 , G06T2207/10016 , G06T2207/20016 , G06T2207/20021
Abstract: In embodiments of spatially coherent nearest neighbor fields, initial matching patches of a nearest neighbor field can be determined at image grid locations of a first digital image and a second digital image. Spatial coherency can be enforced for each matching patch in the second digital image with reference to respective matching patches in the first digital image based on motion data of neighboring matching patches. A multi-resolution iterative process can then update each spatially coherent matching patch based on overlapping grid regions of the matching patches that are evaluated for matching regions of the first and second digital images. An optimal, spatially coherent matching patch can be selected for each of the image grid locations of the first and second digital images based on iterative interaction to enforce the spatial coherency of each matching patch and the multi-resolution iterative process to update each spatially coherent matching patch.
Abstract translation: 在空间相干最近邻域的实施例中，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初始匹配块。 基于相邻匹配补丁的运动数据，参考第一数字图像中的相应匹配补丁，可以针对第二数字图像中的每个匹配补丁实施空间一致性。 然后，多分辨率迭代过程可以基于为第一和第二数字图像的匹配区域评估的匹配块的重叠网格区域来更新每个空间相干匹配块。 可以基于迭代交互来选择针对第一和第二数字图像的每个图像网格位置的最佳空间相干匹配块，以强制每个匹配块的空间一致性和多分辨率迭代过程以更新每个空间相干匹配 补丁。
-
公开(公告)号：US20140254881A1
公开(公告)日：2014-09-11
申请号：US13794219
申请日：2013-03-11
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Hailin Jin , Zhuoyuan Chen , Zhe Lin , Scott D. Cohen
IPC: G06K9/62
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。
-
公开(公告)号：US20140153819A1
公开(公告)日：2014-06-05
申请号：US13691190
申请日：2012-11-30
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Zhe Lin , Xin Lu , Jonathan Brandt , Hailin Jin
IPC: G06T5/50
CPC classification number: G06T5/002 , G06T2207/20081 , G06T2207/20084
Abstract: Systems and methods are provided for providing learned, piece-wise patch regression for image enhancement. In one embodiment, an image manipulation application generates training patch pairs that include training input patches and training output patches. Each training patch pair includes a respective training input patch from a training input image and a respective training output patch from a training output image. The training input image and the training output image include at least some of the same image content. The image manipulation application determines patch-pair functions from at least some of the training patch pairs. Each patch-pair function corresponds to a modification to a respective training input patch to generate a respective training output patch. The image manipulation application receives an input image generates an output image from the input image by applying at least some of the patch-pair functions based on at least some input patches of the input image.
Abstract translation: 提供了系统和方法，用于为图像增强提供学习的分段补丁回归。 在一个实施例中，图像处理应用产生训练补丁对，其包括训练输入补丁和训练输出补丁。 每个训练补丁对包括来自训练输入图像的相应训练输入补丁和来自训练输出图像的相应训练输出补丁。 训练输入图像和训练输出图像包括至少一些相同的图像内容。 图像处理应用程序从至少一些训练补丁对确定补丁对功能。 每个补丁对功能对应于对相应的训练输入补丁的修改以生成相应的训练输出补丁。 图像处理应用程序接收输入图像，基于输入图像的至少一些输入图像块，通过应用至少一些补丁对功能，从输入图像生成输出图像。
-
Patent Agency Ranking
公开(公告)号：US20140098988A1
公开(公告)日：2014-04-10
申请号：US13645453
申请日：2012-10-04
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Jonathan W. Brandt , Zhe Lin , Lubomir D. Bourdev , Vuong Le
CPC classification number: G06K9/00281 , G06K9/6209
Abstract: Various embodiments of methods and apparatus for feature point localization are disclosed. An object in an input image may be detected. A profile model may be applied to determine feature point locations for each object component of the detected object. Applying the profile model may include globally optimizing the feature points for each object component to find a global energy minimum. A component-based shape model may be applied to update the respective feature point locations for each object component.
Abstract translation: 公开了用于特征点定位的方法和装置的各种实施例。 可以检测输入图像中的对象。 可以应用轮廓模型来确定检测到的对象的每个对象分量的特征点位置。 应用轮廓模型可以包括全局优化每个对象分量的特征点以找到全局能量最小值。 可以应用基于组件的形状模型来更新每个对象组件的各个特征点位置。
-
77.发明申请公开(公告)号：US20190110002A1
公开(公告)日：2019-04-11
申请号：US15730632
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 view switching of video on a computing device. In an example, a video processing application executed on the computing device receives a stream of video data. The video processing application renders a major view on a display of the computing device. The major view presents a video from the stream of video data. The video processing application inputs the stream of video data to a deep learning system and receives back information that identifies a cropped video from the video based on a composition score of the cropped video, while the video is presented in the major view. The composition score is generated by the deep learning system. The video processing application renders a sub-view on a display of the device, the sub-view presenting the cropped video. The video processing application renders the cropped video in the major view based on a user interaction with the sub-view.
-
公开(公告)号：US10216766B2
公开(公告)日：2019-02-26
申请号：US15463769
申请日：2017-03-20
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Zhe Lin , Xiaohui Shen , Jianming Zhang , Hailin Jin , Yingwei Li
Abstract: A framework is provided for associating images with topics utilizing embedding learning. The framework is trained utilizing images, each having multiple visual characteristics and multiple keyword tags associated therewith. Visual features are computed from the visual characteristics utilizing a convolutional neural network and an image feature vector is generated therefrom. The keyword tags are utilized to generate a weighted word vector (or “soft topic feature vector”) for each image by calculating a weighted average of word vector representations that represent the keyword tags associated with the image. The image feature vector and the soft topic feature vector are aligned in a common embedding space and a relevancy score is computed for each of the keyword tags. Once trained, the framework can automatically tag images and a text-based search engine can rank image relevance with respect to queried keywords based upon predicted relevancy scores.
-
公开(公告)号：US20190035083A1
公开(公告)日：2019-01-31
申请号：US16116609
申请日：2018-08-29
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Chenxi Liu
CPC classification number: G06T7/11 , G06F17/2715 , G06F17/277 , G06F17/2785 , G06K9/00664 , G06K9/6274 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T2207/20084 , G06T2207/20101 , 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：US20190026609A1
公开(公告)日：2019-01-24
申请号：US15658265
申请日：2017-07-24
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Zhe Lin , Radomir Mech , Jian Ren
Abstract: Techniques and systems are described to determine personalized digital image aesthetics in a digital medium environment. In one example, a personalized offset is generated to adapt a generic model for digital image aesthetics. A generic model, once trained, is used to generate training aesthetics scores from a personal training data set that corresponds to an entity, e.g., a particular user, group of users, and so on. The image aesthetics system then generates residual scores (e.g., offsets) as a difference between the training aesthetics score and the personal aesthetics score for the personal training digital images. The image aesthetics system then employs machine learning to train a personalized model to predict the residual scores as a personalized offset using the residual scores and personal training digital images.
-
-
-
-
-
-
-
-
-
Search Results
197
records
(took 0.025 seconds)
