IMAGE PROCESSING METHOD AND APPARATUS, COMPUTER STORAGE MEDIUM, AND ELECTRONIC DEVICE

    公开(公告)号:EP4044122A1

    公开(公告)日:2022-08-17

    申请号:EP21822842.7

    申请日:2021-05-12

    发明人: LI, Qi HUANG, Qian

    IPC分类号: G06T15/50 G06T17/00

    摘要: Disclosed are an image processing method and apparatus, a computer storage medium, and an electronic device, which relate to the field of image processing. The method comprises: acquiring a diffuse map, and acquiring a shadow texel, located in a shadow area, in the diffuse map (S310); querying an average color lookup table according to spatial coordinate information of the shadow texel, and according to a query result, determining an average brightness difference corresponding to the shadow texel (S320); and determining restored color information according to the average brightness difference and color information corresponding to the shadow texel, and according to the restored color information, restoring the color information of the shadow texel (S330). By means of the method, a shadow in a diffuse map can be effectively removed, such that a model can be used in scenarios with any lighting conditions.

    CREATION OF 3D REFERENCE OUTLINES
    86.
    发明公开

    公开(公告)号:EP4030392A1

    公开(公告)日:2022-07-20

    申请号:EP21151879.0

    申请日:2021-01-15

    摘要: The disclosure relates to a method for creating a reference outline (3) of a first object (2),
    the method comprising the steps:
    - Obtaining (S1) a first representation of a first three-dimensional environment including the first object (2), wherein the first representation includes a depth information and a spatial information of the first three-dimensional environment,
    - determining (S2) a multitude of reference points (4) by using results of analysing a first user (1) interaction and the first representation,
    - determining (S3a) the reference outline (3) of the first object (2), wherein the reference outline (3) comprises at least one line,
    wherein each of the at least one lines comprises at least one of the multitude of reference points (4), and
    - storing (S4) the reference outline (3).
    The disclosure further relates to a computer program product and a computer-readable storage medium.

    VIEWPOINT IMAGE PROCESSING METHOD AND RELATED DEVICE

    公开(公告)号:EP4024343A1

    公开(公告)日:2022-07-06

    申请号:EP20867313.7

    申请日:2020-06-09

    IPC分类号: G06T17/00 G06N3/02

    摘要: A viewpoint image processing method and a related device are provided, and relate to the artificial intelligence/computer vision field. The method includes: obtaining a preset quantity of first viewpoint images (S1201); obtaining a geometric feature matrix between the preset quantity of first viewpoint images; generating an adaptive convolution kernel corresponding to each pixel of the preset quantity of first viewpoint images based on the geometric feature matrix and location information of a to-be-synthesized second viewpoint image, where the location information represents a viewpoint location of the second viewpoint image; generating the preset quantity of to-be-processed virtual composite pixel matrices based on the adaptive convolution kernels and the pixels of the preset quantity of existing viewpoint images (S1204); and synthesizing the second viewpoint image by using the preset quantity of to-be-processed virtual composite pixel matrices (S1205). The method can improve efficiency and quality of synthesizing the second viewpoint image.

    GENERATION OF VIRTUAL VIEWPOINT IMAGES
    90.
    发明公开

    公开(公告)号:EP4012661A1

    公开(公告)日:2022-06-15

    申请号:EP22150472.3

    申请日:2017-10-20

    发明人: TAKAMA, Yasufumi

    摘要: An image processing system comprising: image obtaining means for obtaining a plurality of images captured from a plurality of directions by a plurality of image capturing apparatuses; acceptance means for accepting an input corresponding to an operation for specifying a virtual viewpoint; and generation means for generating a plurality of virtual viewpoint images based on the plurality of images obtained by the image obtaining means and the input accepted by the acceptance means, the plurality of virtual viewpoint images including a first virtual viewpoint image and a second virtual viewpoint image, wherein a number of image capturing apparatuses corresponding to an image to be used by the generation means to generate the second virtual viewpoint image is larger than a number of image capturing apparatuses corresponding to an image to be used by the generation means to generate the first virtual viewpoint image, and wherein a plurality of image capturing apparatuses corresponding to images to be used by the generation means to generate the second virtual viewpoint image comprises an image capturing apparatus different from an image capturing apparatus corresponding to an image to be used by the generation means to generate the first virtual viewpoint image.