APPARATUS AND METHOD FOR IMAGE OUTPAINTING BASED ON LEARNING OF A SINGLE INPUT IMAGE

    公开(公告)号:US20230169628A1

    公开(公告)日:2023-06-01

    申请号:US17990880

    申请日:2022-11-21

    Abstract: Disclosed herein are an apparatus and method for image outpainting based on learning of a single input image. The apparatus generates multiple extended images from an input image using multiple noise vectors, inputs a first extended image, among the multiple extended images, the input image, and an image acquired by horizontally flipping the input image and thereby trains a discriminator network such that the loss of a generative adversarial network is minimized, and learns the multiple extended images such that the sum of two differences is minimized, the first one being the difference between the input image and the center region of a second extended image, and the second one being the difference between images acquired by vertically segmenting the input image and flipping the segments and the left and right regions of a third extended image.

    APPARATUS AND METHOD FOR CAMERA TRACKING
    7.
    发明申请
    APPARATUS AND METHOD FOR CAMERA TRACKING 审中-公开
    摄像机跟踪的装置和方法

    公开(公告)号:US20140241576A1

    公开(公告)日:2014-08-28

    申请号:US14102096

    申请日:2013-12-10

    CPC classification number: G06T7/248 G06T7/55 G06T2207/30204

    Abstract: A camera tracking apparatus including a sequence image input unit configured to obtain one or more image frames by decoding an input two-dimensional image, a two-dimensional feature point tracking unit configured to obtain a feature point track by extracting feature points from respective image frames obtained by the sequence image input unit, and comparing the extracted feature points with feature points extracted from a previous image frame, to connect feature points determined to be similar, and a three-dimensional reconstruction unit configured to reconstruct the feature point track obtained by the two-dimensional feature point tracking unit.

    Abstract translation: 一种相机跟踪装置,包括:序列图像输入单元,被配置为通过解码输入的二维图像来获得一个或多个图像帧;二维特征点跟踪单元,被配置为通过从各个图像帧中提取特征点来获得特征点轨迹 并且将所提取的特征点与从先前图像帧提取的特征点进行比较以连接被确定为相似的特征点,以及三维重建单元,其被配置为重建由所述特征点轨迹获得的特征点轨迹 二维特征点跟踪单元。

    APPARATUS AND METHOD FOR CREATING THREE-DIMENSIONAL VIDEO
    8.
    发明申请
    APPARATUS AND METHOD FOR CREATING THREE-DIMENSIONAL VIDEO 审中-公开
    用于创建三维视频的装置和方法

    公开(公告)号:US20140210943A1

    公开(公告)日:2014-07-31

    申请号:US13973527

    申请日:2013-08-22

    CPC classification number: H04N13/261 H04N13/264

    Abstract: An apparatus for creating a three dimensional video including a cut split unit configured to split an input two-dimensional video into two or more cuts based on a predetermined reference, a manual conversion unit configured to receive a depth value of one of frames that form each of the two or more cuts split by the cut split unit and convert the one frame into a three dimensional form, and an automatic conversion unit configured to convert other frames included in the cuts with reference to the one frame, which is converted into the three dimensional form by the manual conversion unit, into a three dimensional form.

    Abstract translation: 一种用于创建三维视频的装置,包括:分割单元,被配置为基于预定参考将输入的二维视频分割为两个或更多个切割;手动转换单元,被配置为接收形成每个视频的一个帧的深度值 所述两个或更多个切割由所述切割分割单元分割并将所述一个框架转换为三维形状;以及自动转换单元,被配置为参照所述一个框架转换包括在所述切割中的其他框架,所述自动转换单元被转换为三个 三维形式由手动转换单元形成三维形式。

Patent Agency Ranking