公开(公告)号：US09613405B2

公开(公告)日：2017-04-04

申请号：US15187924

申请日：2016-06-21

Applicant: Adobe Systems Incorporated

Inventor： Chih-Yao Hsieh ,  Zhe Lin

IPC: G06K9/40 ,  G06T5/00 ,  G06T3/40 ,  G06T11/00 ,  G06T5/20 ,  G06T11/60

CPC classification number: G06T5/003 ,  G06T3/4053 ,  G06T3/4076 ,  G06T5/00 ,  G06T5/001 ,  G06T5/002 ,  G06T5/20 ,  G06T11/00 ,  G06T11/001 ,  G06T11/60 ,  G06T2207/20021 ,  G06T2207/20024

Abstract: Techniques for enhancing an image using pixel-specific processing are disclosed. An image can be enhanced by updating certain pixels through patch aggregation. Neighboring pixels of a selected pixel are identified. Respective patch values for patches containing the selected pixel are determined. Patch values provide update information for updating the respective pixels in the patch. Relevant patch values for the selected pixel are identified by identifying associated patches of the pixel. Information from the relevant patch values of the selected pixel may be obtained. Using this information, pixel-specific processing may be performed to determine an updated pixel value for the selected pixel or for neighboring pixels of the selected pixel. Pixel-specific processes may be executed for each of the selected or neighboring pixels. These pixel-specific processes can be executed in parallel. Therefore, through the execution of pixel-specific processes, which may be performed concurrently, an enhanced image may be determined.

公开(公告)号：US09607391B2

公开(公告)日：2017-03-28

申请号：US14817731

申请日：2015-08-04

Applicant: Adobe Systems Incorporated

Inventor： Brian Price ,  Zhe Lin ,  Scott Cohen ,  Jimei Yang

IPC: G06K9/34 ,  G06T7/00 ,  G06K9/62

CPC classification number: G06T7/251 ,  G06K9/6215 ,  G06T7/11 ,  G06T7/174 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/20081

Abstract: Systems and methods are disclosed herein for using one or more computing devices to automatically segment an object in an image by referencing a dataset of already-segmented images. The technique generally involves identifying a patch of an already-segmented image in the dataset based on the patch of the already-segmented image being similar to an area of the image including a patch of the image. The technique further involves identifying a mask of the patch of the already-segmented image, the mask representing a segmentation in the already-segmented image. The technique also involves segmenting the object in the image based on at least a portion of the mask of the patch of the already-segmented image.

公开(公告)号：US20170039723A1

公开(公告)日：2017-02-09

申请号：US14817731

申请日：2015-08-04

Applicant: Adobe Systems Incorporated

Inventor： Brian Price ,  Zhe Lin ,  Scott Cohen ,  Jimei Yang

IPC: G06T7/00 ,  G06K9/62

CPC classification number: G06T7/251 ,  G06K9/6215 ,  G06T7/11 ,  G06T7/174 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/20081

Abstract: Systems and methods are disclosed herein for using one or more computing devices to automatically segment an object in an image by referencing a dataset of already-segmented images. The technique generally involves identifying a patch of an already-segmented image in the dataset based on the patch of the already-segmented image being similar to an area of the image including a patch of the image. The technique further involves identifying a mask of the patch of the already-segmented image, the mask representing a segmentation in the already-segmented image. The technique also involves segmenting the object in the image based on at least a portion of the mask of the patch of the already-segmented image.

Abstract translation: 本文公开的系统和方法用于使用一个或多个计算设备通过参考已经分割的图像的数据集自动地分割图像中的对象。 该技术通常涉及基于已经分段的图像的片段类似于包括图像的片段的图像的区域来识别数据集中的已经分割的图像的片段。 该技术还涉及识别已经分割的图像的斑块的掩模，该掩码表示已经分割的图像中的分割。 该技术还涉及基于已经分割的图像的补片的掩模的至少一部分来分割图像中的对象。

公开(公告)号：US20170031571A1

公开(公告)日：2017-02-02

申请号：US15291462

申请日：2016-10-12

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Byungmoon Kim ,  Yuan Gao

IPC: G06F3/0484 ,  G06F3/0481 ,  G06T5/00 ,  G06F3/0488

CPC classification number: G06F3/04845 ,  G06F3/041 ,  G06F3/04817 ,  G06F3/04847 ,  G06F3/0488 ,  G06F3/04883 ,  G06T5/001 ,  G06T5/002 ,  G06T5/003 ,  G06T2200/24

Abstract: This document describes techniques and apparatuses for area-dependent image enhancement. These techniques are capable of enabling selection, through a touch-enabled mobile-device display, of an area of a photographic image through movement of a spatially-variable implement, such as brush icon moved over the image. Selected areas can be enhanced differently than other areas, such as to apply sharpening to the selected area and blurring to a non-selected area.

Abstract translation: 本文档描述了区域依赖图像增强的技术和装置。 这些技术能够通过诸如移动在图像上的画笔图标的空间可变的工具的移动，使得能够通过启用触摸的移动设备显示来选择摄影图像的区域。 所选区域可以与其他区域不同地增强，例如对所选择的区域应用锐化和模糊到未选择的区域。

公开(公告)号：US20160364625A1

公开(公告)日：2016-12-15

申请号：US14735822

申请日：2015-06-10

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Xiaohui Shen ,  Kalyan Sunkavalli ,  Joon-Young Lee

IPC: G06K9/46 ,  G06T7/60 ,  G06K9/52 ,  G06T7/40 ,  G06K9/62

CPC classification number: G06T7/60 ,  G06K9/00624 ,  G06T7/90 ,  G06T11/001

Abstract: Systems and methods are provided for content-based selection of style examples used in image stylization operations. For example, training images can be used to identify example stylized images that will generate high-quality stylized images when stylizing input images having certain types of semantic content. In one example, a processing device determines which example stylized images are more suitable for use with certain types of semantic content represented by training images. In response to receiving or otherwise accessing an input image, the processing device analyzes the semantic content of the input image, matches the input image to at least one training image with similar semantic content, and selects at least one example stylized image that has been previously matched to one or more training images having that type of semantic content. The processing device modifies color or contrast information for the input image using the selected example stylized image.

Abstract translation: 提供了系统和方法用于基于内容的图像样式化操作中使用的样式示例的选择。 例如，训练图像可用于识别示例风格化图像，其将在对具有某些类型的语义内容的输入图像进行风格化时生成高质量的程式化图像。 在一个示例中，处理设备确定哪个示例风格化图像更适合于使用由训练图像表示的某些类型的语义内容。 响应于接收或以其他方式访问输入图像，处理设备分析输入图像的语义内容，将输入图像与具有相似语义内容的至少一个训练图像匹配，并且选择至少一个先前已经具有的示例风格化图像 与具有该类型的语义内容的一个或多个训练图像匹配。 处理装置使用所选择的示例风格化图像修改输入图像的颜色或对比度信息。

公开(公告)号：US20160350930A1

公开(公告)日：2016-12-01

申请号：US14724660

申请日：2015-05-28

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Scott D. Cohen ,  Peng Wang ,  Xiaohui Shen ,  Brian L. Price

IPC: G06T7/00 ,  G06K9/66 ,  H04N13/02

CPC classification number: G06K9/66 ,  G06K9/00664 ,  G06K9/4628 ,  G06K9/6272 ,  G06T7/50 ,  G06T2207/20081

Abstract: Joint depth estimation and semantic labeling techniques usable for processing of a single image are described. In one or more implementations, global semantic and depth layouts are estimated of a scene of the image through machine learning by the one or more computing devices. Local semantic and depth layouts are also estimated for respective ones of a plurality of segments of the scene of the image through machine learning by the one or more computing devices. The estimated global semantic and depth layouts are merged with the local semantic and depth layouts by the one or more computing devices to semantically label and assign a depth value to individual pixels in the image.

Abstract translation: 描述了可用于处理单个图像的联合深度估计和语义标注技术。 在一个或多个实现中，通过一个或多个计算设备的机器学习来估计图像的场景的全局语义和深度布局。 还通过一个或多个计算设备的机器学习来估计图像场景的多个片段中的各个片段的局部语义和深度布局。 估计的全局语义和深度布局由一个或多个计算设备与本地语义和深度布局合并，以语义地标记并分配图像中的各个像素的深度值。

公开(公告)号：US09454712B2

公开(公告)日：2016-09-27

申请号：US14510000

申请日：2014-10-08

Applicant: Adobe Systems Incorporated

Inventor： Zhe Lin ,  Radomir Mech ,  Xiaohui Shen ,  Brian L. Price ,  Jianming Zhang

IPC: G06K9/46 ,  G06T11/60

CPC classification number: G06K9/4671 ,  G06T11/60

Abstract: Saliency map computation is described. In one or more implementations, a base saliency map is generated for an image of a scene. The base saliency map may be generated from intermediate saliency maps computed for boundary regions of the image. Each of the intermediate saliency maps may represent visual saliency of portions of the scene that are captured in the corresponding boundary region. The boundary regions may include, for instance, a top boundary region, a bottom boundary region, a left boundary region, and a right boundary region. Further, the intermediate saliency maps may be combined in such a way that an effect of a foreground object on the saliency map is suppressed. The foreground objects for which the effect is suppressed are those that occupy a majority of one of the boundary regions.

Abstract translation: 描述了显着地图计算。 在一个或多个实现中，为场景的图像生成基本显着图。 可以从为图像的边界区域计算的中间显着图生成基本显着图。 每个中间显着图可以表示在相应边界区域中捕获的场景的部分的视觉显着性。 边界区域可以包括例如顶边界区域，底边界区域，左边界区域和右边界区域。 此外，中间显着图可以以这样的方式组合，即前景对象对显着图的影响被抑制。 效果被抑制的前景对象是占据边界区域中的大多数的那些。

公开(公告)号：US09396522B2

公开(公告)日：2016-07-19

申请号：US14339874

申请日：2014-07-24

Applicant: Adobe Systems Incorporated

Inventor： Chih-Yao Hsieh ,  Zhe Lin

IPC: G06K9/40 ,  G06T5/00 ,  G06T3/40 ,  G06T11/00

CPC classification number: G06T5/003 ,  G06T3/4053 ,  G06T3/4076 ,  G06T5/00 ,  G06T5/001 ,  G06T5/002 ,  G06T5/20 ,  G06T11/00 ,  G06T11/001 ,  G06T11/60 ,  G06T2207/20021 ,  G06T2207/20024

Abstract: Techniques for enhancing an image using pixel-specific processing. An image can be enhanced by updating selected pixels through patch aggregation. Respective patch values for patches of any size of the image are determined. Patch values provide update information for updating the respective pixels in the patch. Relevant patch values for the selected pixel are identified by identifying associated patches of the pixel. Information from the relevant patch values of the selected pixel may be obtained by averaging the relevant patch values or determining the maximum or minimum patch value. Using this information, pixel-specific processing may be performed to determine an updated pixel value for the selected pixel. Pixel-specific processes may be executed for each of the selected pixels. These pixel-specific processes can be executed in parallel. Therefore, through the execution of pixel-specific processes, which may be performed concurrently, an enhanced image may be determined.

Abstract translation: 使用像素特定处理来增强图像的技术。 通过补丁聚合更新所选像素可以增强图像。 确定任何尺寸图像的补丁的各个补丁值。 补丁值提供更新补丁中各个像素的更新信息。 通过识别像素的相关补丁来识别所选像素的相关补丁值。 可以通过对相关补丁值进行平均或确定最大或最小补丁值来获得来自所选像素的相关补丁值的信息。 使用该信息，可以执行像素特定处理以确定所选择的像素的更新的像素值。 可以针对每个所选择的像素执行像素特定的处理。 这些像素特定的处理可以并行执行。 因此，通过执行可以同时执行的像素特定的处理，可以确定增强图像。

公开(公告)号：US20160148078A1

公开(公告)日：2016-05-26

申请号：US14549350

申请日：2014-11-20

Applicant: Adobe Systems Incorporated

Inventor： Xiaohui Shen ,  Haoxiang Li ,  Zhe Lin ,  Jonathan W. Brandt

IPC: G06K9/66 ,  G06K9/46 ,  G06K9/62 ,  G06N3/04

CPC classification number: G06K9/66 ,  G06K9/4628 ,  G06K9/6267 ,  G06K9/6272 ,  G06N3/04 ,  G06N3/0454

Abstract: A convolutional neural network is trained to analyze input data in various different manners. The convolutional neural network includes multiple layers, one of which is a convolution layer that performs a convolution, for each of one or more filters in the convolution layer, of the filter over the input data. The convolution includes generation of an inner product based on the filter and the input data. Both the filter of the convolution layer and the input data are binarized, allowing the inner product to be computed using particular operations that are typically faster than multiplication of floating point values. The possible results for the convolution layer can optionally be pre-computed and stored in a look-up table. Thus, during operation of the convolutional neural network, rather than performing the convolution on the input data, the pre-computed result can be obtained from the look-up table

Abstract translation: 训练卷积神经网络以各种不同的方式分析输入数据。 卷积神经网络包括多个层，其中之一是卷积层，其对于卷积层中的一个或多个滤波器的每一个，通过输入数据执行滤波器的卷积。 卷积包括基于滤波器和输入数据生成内积。 卷积层的滤波器和输入数据都被二值化，允许使用通常快于浮点值乘法的特定运算来计算内积。 可以可选地预先计算卷积层的可能结果并将其存储在查找表中。 因此，在卷积神经网络的操作期间，不是对输入数据执行卷积，所以可以从查找表中获得预先计算的结果

公开(公告)号：US09311690B2

公开(公告)日：2016-04-12

申请号：US14205027

申请日：2014-03-11

Applicant: Adobe Systems Incorporated

Inventor： Hailin Jin ,  Zhuoyuan Chen ,  Scott D. Cohen ,  Jianchao Yang ,  Zhe Lin

IPC: G06K9/40 ,  G06T3/40 ,  G06T5/00 ,  G06T5/50 ,  G06T5/20 ,  G06T7/20 ,  H04N5/14

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。