METHOD AND APPARATUS FOR GENERATING SPECIAL-EFFECT VIDEO, AND ELECTRONIC DEVICE AND STORAGE MEDIUM

    公开(公告)号:EP4462767A1

    公开(公告)日:2024-11-13

    申请号:EP23752305.5

    申请日:2023-02-06

    发明人: LU, Zhixiong

    摘要: Provided in the present disclosure are a method and apparatus for generating a special-effect video, and an electronic device and a storage medium. The method comprises: when it is detected that a special-effect generation condition is met, acquiring at least two video frames to be processed which are associated with the current moment; on the basis of facial images of target objects in said at least two video frames, generating a target facial dynamic graph, and fusing the target facial dynamic graph into a target special effect, so as to obtain a target special-effect graph; and on the basis of the target special-effect graph, and said video frames corresponding to the current moment, determining a special-effect video frame in a target special-effect video.

    SYSTEM AND METHOD FOR EFFICIENTLY CHECKING MEDIA CONTENT FOR ERRORS

    公开(公告)号:EP4422186A1

    公开(公告)日:2024-08-28

    申请号:EP24153462.7

    申请日:2024-01-23

    摘要: A system and a method are for comparing video content with different attributes. The method includes determining for a first rendition of video content a first value for each of a plurality of video attributes of the first rendition of the video content; determining for a second rendition of the video content a second value for each of the video attributes of the second rendition of the video content, the video attributes of the first and second renditions including parameters associated with a playout of the video content; identifying a first one of the video attributes for which the first value is different from the second value; determining scaling or adjustment parameters for matching or normalizing the first and second values of the first video attribute; generating a transformed rendition of at least the first rendition having an adjusted value for the first video attribute so that the video attributes of a transformed first rendition match the video attributes of the second rendition or a transformed second rendition; and performing a comparative analysis between the transformed first rendition and the second rendition or the transformed second rendition to identify frames in which a comparative performance metric indicates an error or issue in the first rendition or the second rendition.