Unified slider control for modifying multiple image properties
    21.
    发明授权
    Unified slider control for modifying multiple image properties 有权
    用于修改多个图像属性的统一滑块控件

    公开(公告)号:US09131192B2

    公开(公告)日:2015-09-08

    申请号:US13629514

    申请日:2012-09-27

    Applicant: Apple Inc.

    Abstract: Some embodiments provide a novel user interface (UI) tool that is a unified slider control, which includes multiple sliders that slide along a region. The region is a straight line in some embodiments, while it is an angular arc in other embodiments. In some embodiments, the unified slider control is used in a media editing application to allow a user to modify several different properties of the image by moving several different sliders along the region. Each slider is associated with a property of the image. A position of the slider in the region corresponds to a value of the property associated with the slider.

    Abstract translation: 一些实施例提供了一种新颖的用户界面(UI)工具,其是统一的滑块控件,其包括沿着区域滑动的多个滑块。 在一些实施例中,该区域是直线,而在其他实施例中该区域是一个角弧。 在一些实施例中,在媒体编辑应用中使用统一滑块控件,以允许用户通过沿着该区域移动若干不同的滑块来修改图像的若干不同属性。 每个滑块与图像的属性相关联。 滑块在该区域中的位置对应于与滑块相关联的属性的值。

    Method and system for multi-stage auto-enhancement of photographs
    22.
    发明授权
    Method and system for multi-stage auto-enhancement of photographs 有权
    多阶段自动增强照片的方法和系统

    公开(公告)号:US08958638B2

    公开(公告)日:2015-02-17

    申请号:US13629551

    申请日:2012-09-27

    Applicant: Apple Inc.

    CPC classification number: G06T5/007 G06T5/40 G06T2207/10004

    Abstract: Some embodiments of the image editing and organizing application described herein provide a multi-stage automatic enhancement process. The process takes an input image and feeds it through multiple different enhancement operations. The multiple enhancement operations of some embodiments are carried out in a particular order. In some embodiments, the particular order starts with exposure adjustment, then a white balance adjustment, then a vibrancy adjustment, then a tonal response curve adjustment, then a shadow lift adjustment.

    Abstract translation: 本文描述的图像编辑和组织应用的一些实施例提供了多阶段自动增强过程。 该过程需要输入图像并通过多个不同的增强操作进行馈送。 一些实施例的多重增强操作以特定顺序执行。 在一些实施例中,特定顺序从曝光调整开始,然后进行白平衡调整,然后进行活力调整,然后进行音调响应曲线调整,然后进行阴影升降调整。

    Applying a Realistic Artistic Texture to Images
    23.
    发明申请
    Applying a Realistic Artistic Texture to Images 有权
    将现实艺术纹理应用于图像

    公开(公告)号:US20140071148A1

    公开(公告)日:2014-03-13

    申请号:US13834064

    申请日:2013-03-15

    Applicant: APPLE INC.

    CPC classification number: G06T11/001 G09G5/02 H04N1/6058

    Abstract: Techniques are disclosed to provide user control over the manipulation of a digital image. The disclosed techniques enable a user to apply various textures that mimic traditional artistic media to a selected image. User selection of a texture level results in the blending of texturized versions of the selected image in accordance with the selected texture level. User selection of a color level results in the adjustment of color properties of the selected image that are included in the output image. Control of the image selection, texture type selection, texture level selection, and color level selection may be provided through an intuitive graphical user interface.

    Abstract translation: 公开了提供用户对数字图像的操纵的控制的技术。 所公开的技术使得用户能够将模仿传统艺术媒体的各种纹理应用于所选择的图像。 纹理级别的用户选择导致根据所选纹理级别混合所选图像的纹理化版本。 用户选择的颜色级别导致所输入图像中包含的所选图像的颜色属性的调整。 可以通过直观的图形用户界面来提供图像选择,纹理类型选择,纹理等级选择和颜色级别选择的控制。

    COLOR BALANCE TOOLS FOR EDITING IMAGES
    24.
    发明申请
    COLOR BALANCE TOOLS FOR EDITING IMAGES 有权
    用于编辑图像的彩色平衡工具

    公开(公告)号:US20130329994A1

    公开(公告)日:2013-12-12

    申请号:US13629529

    申请日:2012-09-27

    Applicant: APPLE INC.

    Abstract: Some embodiments provide a method for color balancing an image. The method receives a first selection of a first mode of a color balance tool that includes several different color balance modes. Each color balance mode is for applying color balance operations to the image. The method uses the first mode of the color balance tool to apply a first set of color balance operations to the image. The method receives a second selection to switch from the first mode to a second mode of the color balance tool. The method uses the second mode of the color balance tool to apply a second set of color balance operations to the image.

    Abstract translation: 一些实施例提供了一种用于颜色平衡图像的方法。 该方法接收包括若干不同颜色平衡模式的颜色平衡工具的第一模式的第一选择。 每种颜色平衡模式都是用于对图像进行颜色平衡操作。 该方法使用颜色平衡工具的第一模式将第一组色平衡操作应用于图像。 该方法接收从第一模式切换到颜色平衡工具的第二模式的第二选择。 该方法使用颜色平衡工具的第二模式将第二组颜色平衡操作应用于图像。

    METHOD AND INTERFACE FOR CONVERTING IMAGES TO GRAYSCALE

    公开(公告)号:US20130236091A1

    公开(公告)日:2013-09-12

    申请号:US13629549

    申请日:2012-09-27

    Applicant: APPLE INC.

    Abstract: A method and apparatus for generating a grayscale image. The method and apparatus receive a single value. From the single value, the method and apparatus generate a set of grayscale weighting values. The method and apparatus generate the grayscale based on a color image and the set of grayscale weighting values. By limiting the number of values to a single value, the method and apparatus prevents a user from arbitrarily selecting a number of possible weighting values which could result in a grayscale image that is too dim or too bright. This single control method and apparatus quickly and efficiently produces a grayscale image that is neither too bright nor too dim.

    GENERATING REALISTIC SYNTHETIC DATA WITH ADVERSARIAL NETS

    公开(公告)号:US20230081346A1

    公开(公告)日:2023-03-16

    申请号:US18046871

    申请日:2022-10-14

    Applicant: Apple Inc.

    Abstract: A generative network may be learned in an adversarial setting with a goal of modifying synthetic data such that a discriminative network may not be able to reliably tell the difference between refined synthetic data and real data. The generative network and discriminative network may work together to learn how to produce more realistic synthetic data with reduced computational cost. The generative network may iteratively learn a function that synthetic data with a goal of generating refined synthetic data that is more difficult for the discriminative network to differentiate from real data, while the discriminative network may be configured to iteratively learn a function that classifies data as either synthetic or real. Over multiple iterations, the generative network may learn to refine the synthetic data to produce refined synthetic data on which other machine learning models may be trained.

Patent Agency Ranking