-
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。
-
172.发明授权公开(公告)号：US09569822B2
公开(公告)日：2017-02-14
申请号：US14990656
申请日：2016-01-07
Applicant: Adobe Systems Incorporated
Inventor： Chih-Yao Hsieh , Yuyan Song , Zhe Lin
CPC classification number: G06T5/002 , G06T5/20 , G06T7/90 , G06T2207/10024 , G06T2207/20024 , G06T2207/20182
Abstract: In embodiments of removing noise from an image via efficient patch distance computations, weights are computed for patches of pixels in a digital image, and the computed weights are multiplied by respective offset values of offset images that are pixelwise shifted images of the entire digital image. The weights can be applied to the pixels in the digital image on a patch-by-patch basis to restore values of the pixels. Additionally, the digital image can be pixelwise shifted to generate the offset images of the digital image, and the digital image is compared to the offset images. Lookup tables of pixel values can be generated based on the comparisons of the digital image to the offset images, and integral images generated from the lookup tables. Distances to the patches of pixels in the digital image are computed from the integral images, and the computed weights are based on the computed distances.
Abstract translation: 在通过有效的贴片距离计算从图像去除噪声的实施例中，为数字图像中的像素块计算权重，并且将所计算的权重乘以作为整个数字图像的像素移位图像的偏移图像的各个偏移值。 可以在逐个补丁的基础上将权重应用于数字图像中的像素，以恢复像素的值。 此外，数字图像可以被像素移位以产生数字图像的偏移图像，并且将数字图像与偏移图像进行比较。 可以基于数字图像与偏移图像的比较以及从查找表生成的积分图像来生成像素值的查找表。 从积分图像计算数字图像中的像素块的距离，并且计算的权重基于计算的距离。
-
公开(公告)号：US09536293B2
公开(公告)日：2017-01-03
申请号：US14447290
申请日：2014-07-30
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： Zhe Lin , Hailin Jin , Jianchao Yang
CPC classification number: G06T7/0002 , G06K9/4628 , G06K9/6255 , G06K9/6277 , G06K9/66 , G06N3/0454
Abstract: Deep convolutional neural networks receive local and global representations of images as inputs and learn the best representation for a particular feature through multiple convolutional and fully connected layers. A double-column neural network structure receives each of the local and global representations as two heterogeneous parallel inputs to the two columns. After some layers of transformations, the two columns are merged to form the final classifier. Additionally, features may be learned in one of the fully connected layers. The features of the images may be leveraged to boost classification accuracy of other features by learning a regularized double-column neural network.
Abstract translation: 深卷积神经网络接收图像的局部和全局表示作为输入，并通过多个卷积和完全连接的层学习特定特征的最佳表示。 双列神经网络结构将每个本地和全局表示都接收到两列异构并行输入。 在一些转换层之后，两列合并形成最终的分类器。 另外，可以在完全连接的层之一中学习特征。 可以通过学习正则化的双列神经网络来利用图像的特征来提高其他特征的分类精度。
-
公开(公告)号：US09406110B2
公开(公告)日：2016-08-02
申请号：US14968075
申请日：2015-12-14
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Radomir Mech , Xiaohui Shen , Chen Fang
CPC classification number: G06T5/003 , G06F17/30256 , G06F17/3053 , G06T7/00 , G06T11/60 , G06T2207/10004 , G06T2207/10016 , G06T2207/20016 , G06T2207/20092 , G06T2207/20132 , G06T2207/30168 , G06T2210/22
Abstract: Cropping boundary simplicity techniques are described. In one or more implementations, multiple candidate cropping s of a scene are generated. For each of the candidate croppings, a score is calculated that is indicative of a boundary simplicity for the candidate cropping. To calculate the boundary simplicity, complexity of the scene along a boundary of a respective candidate cropping is measured. The complexity is measured, for instance, using an average gradient, an image edge map, or entropy along the boundary. Values indicative of the complexity may be derived from the measuring. The candidate croppings may then be ranked according to those values. Based on the scores calculated to indicate the boundary simplicity, one or more of the candidate croppings may be chosen e.g., to present the chosen croppings to a user for selection.
Abstract translation: 描述边界简单技术。 在一个或多个实现中，生成场景的多个候选裁剪。 对于每个候选作物，计算表示候选种植的边界简单性的分数。 为了计算边界简单性，测量沿着相应候选剪切的边界的场景的复杂性。 测量复杂度，例如，使用沿着边界的平均梯度，图像边缘图或熵。 表示复杂性的值可以从测量得出。 然后可以根据这些值对候选作物进行排序。 基于计算的用于指示边界简单性的分数，可以选择一个或多个候选剪切，以将所选择的剪切呈现给用户进行选择。
-
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。
-
Patent Agency Ranking
公开(公告)号：US20160148079A1
公开(公告)日：2016-05-26
申请号：US14550800
申请日：2014-11-21
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Haoxiang Li , Zhe Lin , Jonathan W. Brandt
CPC classification number: G06K9/00288 , G06K9/4628 , G06K9/6257 , G06N3/0454
Abstract: Different candidate windows in an image are identified, such as by sliding a rectangular or other geometric shape of different sizes over an image to identify portions of the image (groups of pixels in the image). The candidate windows are analyzed by a set of convolutional neural networks, which are cascaded so that the input of one convolutional neural network layer is based on the input of another convolutional neural network layer. Each convolutional neural network layer drops or rejects one or more candidate windows that the convolutional neural network layer determines does not include an object (e.g., a face). The candidate windows that are identified as including an object (e.g., a face) are analyzed by another one of the convolutional neural network layers. The candidate windows identified by the last of the convolutional neural network layers are the indications of the objects (e.g., faces) in the image.
Abstract translation: 识别图像中的不同候选窗口，例如通过在图像上滑动不同尺寸的矩形或其他几何形状以识别图像（图像中的像素组）的部分。 候选窗口由一组卷积神经网络进行分析，这些网络级联，使得一个卷积神经网络层的输入基于另一个卷积神经网络层的输入。 每个卷积神经网络层丢弃或拒绝卷积神经网络层确定的一个或多个候选窗口不包括对象（例如，面部）。 识别为包括对象（例如脸部）的候选窗口由另一个卷积神经网络层分析。 由最后的卷积神经网络层识别的候选窗口是图像中的对象（例如，面部）的指示。
-
177.发明申请公开(公告)号：US20160117805A1
公开(公告)日：2016-04-28
申请号：US14990656
申请日：2016-01-07
Applicant: Adobe Systems Incorporated
Inventor： Chih-Yao Hsieh , Yuyan Song , Zhe Lin
CPC classification number: G06T5/002 , G06T5/20 , G06T7/90 , G06T2207/10024 , G06T2207/20024 , G06T2207/20182
Abstract: In embodiments of removing noise from an image via efficient patch distance computations, weights are computed for patches of pixels in a digital image, and the computed weights are multiplied by respective offset values of offset images that are pixelwise shifted images of the entire digital image. The weights can be applied to the pixels in the digital image on a patch-by-patch basis to restore values of the pixels. Additionally, the digital image can be pixelwise shifted to generate the offset images of the digital image, and the digital image is compared to the offset images. Lookup tables of pixel values can be generated based on the comparisons of the digital image to the offset images, and integral images generated from the lookup tables. Distances to the patches of pixels in the digital image are computed from the integral images, and the computed weights are based on the computed distances.
Abstract translation: 在通过有效的贴片距离计算从图像去除噪声的实施例中，为数字图像中的像素块计算权重，并且将所计算的权重乘以作为整个数字图像的像素移位图像的偏移图像的各个偏移值。 可以在逐个补丁的基础上将权重应用于数字图像中的像素，以恢复像素的值。 此外，数字图像可以被像素移位以产生数字图像的偏移图像，并且将数字图像与偏移图像进行比较。 可以基于数字图像与偏移图像的比较以及从查找表生成的积分图像来生成像素值的查找表。 从积分图像计算数字图像中的像素块的距离，并且计算的权重基于计算的距离。
-
公开(公告)号：US20160104055A1
公开(公告)日：2016-04-14
申请号：US14511001
申请日：2014-10-09
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Radomir Mech , Xiaohui Shen , Brian L. Price , Jianming Zhang , Anant Gilra , Jen-Chan Jeff Chien
CPC classification number: G06T3/40 , G06K9/4671 , G06T3/0012 , G06T11/60 , G06T2210/22
Abstract: Image cropping suggestion using multiple saliency maps is described. In one or more implementations, component scores, indicative of visual characteristics established for visually-pleasing croppings, are computed for candidate image croppings using multiple different saliency maps. The visual characteristics on which a candidate image cropping is scored may be indicative of its composition quality, an extent to which it preserves content appearing in the scene, and a simplicity of its boundary. Based on the component scores, the croppings may be ranked with regard to each of the visual characteristics. The rankings may be used to cluster the candidate croppings into groups of similar croppings, such that croppings in a group are different by less than a threshold amount and croppings in different groups are different by at least the threshold amount. Based on the clustering, croppings may then be chosen, e.g., to present them to a user for selection.
Abstract translation: 描述了使用多个显着图的图像裁剪建议。 在一个或多个实现中，针对使用多个不同显着图的候选图像裁剪计算指示为视觉上令人满意的裁剪而建立的视觉特征的分数分数。 评估候选图像裁剪的视觉特征可以指示其组成质量，其保存出现在场景中的内容的程度以及其边界的简单性。 基于分量分数，可以根据每个视觉特征来排列裁剪。 排名可以用于将候选作物聚类成类似的作物的组，使得组中的作物差异小于阈值量，并且不同组中的剪切至少达到阈值量。 基于聚类，可以选择裁剪，例如将其呈现给用户进行选择。
-
公开(公告)号：US20160062731A1
公开(公告)日：2016-03-03
申请号：US14473104
申请日：2014-08-29
Applicant: Adobe Systems Incorporated
Inventor： Zhe Lin , Jonathan Brandt , Xiaohui Shen , Jae-Pil Heo
CPC classification number: G06F7/24 , G06F17/30268 , G06F17/30271 , G06F17/30622
Abstract: Techniques are disclosed for indexing and searching high-dimensional data using inverted file structures and product quantization encoding. An image descriptor is quantized using a form of product quantization to determine which of several inverted lists the image descriptor is to be stored. The image descriptor is appended to the corresponding inverted list with a compact coding using a product quantization encoding scheme. When processing a query, a shortlist is computed that includes a set of candidate search results. The shortlist is based on the orthogonality between two random vectors in high-dimensional spaces. The inverted lists are traversed in the order of the distance between the query and the centroid of a coarse quantizer corresponding to each inverted list. The shortlist is ranked according to the distance estimated by a form of product quantization, and the top images referred to by the ranked shortlist are reported as the search results.
Abstract translation: 公开了用于使用反向文件结构和乘积量化编码索引和搜索高维数据的技术。 使用产品量化的形式量化图像描述符，以确定要存储图像描述符的几个反转列表中的哪一个。 使用产品量化编码方案，使用紧凑编码将图像描述符附加到相应的反转列表。 在处理查询时，计算包括一组候选搜索结果的候选清单。 该候选清单基于高维空间中的两个随机向量之间的正交性。 按照与每个反向列表对应的粗略量化器的查询和质心之间的距离的顺序遍历反向列表。 根据通过产品量化形式估计的距离对候选名单进行排序，并将由排名的候选名单引用的顶部图像报告为搜索结果。
-
公开(公告)号：US20160019440A1
公开(公告)日：2016-01-21
申请号：US14335059
申请日：2014-07-18
Applicant: Adobe Systems Incorporated
Inventor： Xiaohui Shen , Zhe Lin , Jonathan W. Brandt
CPC classification number: G06K9/6256 , G06F17/30247 , G06F17/30253 , G06K9/46 , G06K9/4676 , G06K9/469 , G06N5/04 , G06N99/005
Abstract: Feature interpolation techniques are described. In a training stage, features are extracted from a collection of training images and quantized into visual words. Spatial configurations of the visual words in the training images are determined and stored in a spatial configuration database. In an object detection stage, a portion of features of an image are extracted from the image and quantized into visual words. Then, a remaining portion of the features of the image are interpolated using the visual words and the spatial configurations of visual words stored in the spatial configuration database.
-
-
-
-
-
-
-
-
-
Search Results
197
records
(took 0.024 seconds)
