METHOD AND APPARATUS TO MODEL OBJECTS INCLUDING PARTICLES
    21.
    发明申请
    METHOD AND APPARATUS TO MODEL OBJECTS INCLUDING PARTICLES 审中-公开
    包括颗粒在内的模型对象的方法和装置

    公开(公告)号:US20160140266A1

    公开(公告)日:2016-05-19

    申请号:US14940740

    申请日:2015-11-13

    CPC classification number: G06F17/5009 G06F2217/16

    Abstract: A method and corresponding apparatus to model objects includes detecting an overlapping area between first and second objects each comprising particles. The method and corresponding apparatus also calculate, in the overlapping area, an action force between the first and the second objects. The method and corresponding apparatus model the first object and the second object based on the action force.

    Abstract translation: 用于建模对象的方法和相应装置包括检测每个包括粒子的第一和第二对象之间的重叠区域。 该方法和相应装置还在重叠区域中计算第一和第二对象之间的作用力。 该方法和相应的装置基于动作力来模拟第一对象和第二对象。

    METHOD AND APPARATUS FOR PROCESSING IMAGE
    22.
    发明申请
    METHOD AND APPARATUS FOR PROCESSING IMAGE 审中-公开
    用于处理图像的方法和装置

    公开(公告)号:US20160042558A1

    公开(公告)日:2016-02-11

    申请号:US14820120

    申请日:2015-08-06

    Abstract: An image processing apparatus and method are provided. The image processing method may generate a mask for preventing a virtual light source from being sampled on an area of a current image frame based on virtual light source information of a previous image frame, applying the mask to the current image frame, sampling the virtual light source in the current image frame to which the mask is applied, and rendering the current image frame based on the virtual light source sampled in the current image frame.

    Abstract translation: 提供了一种图像处理装置和方法。 图像处理方法可以基于先前图像帧的虚拟光源信息生成用于防止虚拟光源在当前图像帧的区域上被采样的掩码,将掩模应用于当前图像帧,对虚拟光进行采样 源于应用了掩模的当前图像帧,并且基于在当前图像帧中采样的虚拟光源渲染当前图像帧。

    METHOD AND APPARATUS WITH SUPER RESOLUTION
    27.
    发明公开

    公开(公告)号:US20240153035A1

    公开(公告)日:2024-05-09

    申请号:US18330654

    申请日:2023-06-07

    CPC classification number: G06T3/4076 G06T3/4046

    Abstract: A processor-implemented method includes generating an adjusted reference patch by adjusting a position of a reference patch in a reference image based on a pixel value of a ground truth (GT) patch of a GT image and a pixel value of the reference patch, wherein the GT patch corresponds to a specific region of an input image; generating a super-resolution (SR) image of the input image using a SR model provided an input that is based on the generated adjusted reference patch; and training the SR model based on the SR image and the GT image.

Patent Agency Ranking