ENCODING WITH SIGNALING OF FEATURE MAP DATA
    74.
    发明公开

    公开(公告)号:US20230336758A1

    公开(公告)日:2023-10-19

    申请号:US18339772

    申请日:2023-06-22

    CPC classification number: H04N19/46 H04N19/132

    Abstract: The present disclosure relates to methods and apparatuses for encoding data for (still or video processing into a bitstream). In particular, the data are processed by a network which includes a plurality of cascaded layers. In the processing, feature maps are generated by the layers. The feature maps processed (output) by at least two different layers have different resolutions. In the processing, a layer is selected, out of the cascaded layers, which is different from the layer generating the feature map of the lowest resolution (e.g. latent space). The bitstream includes information related to the selected layer. With this approach, scalable processing which may operate on different resolutions is provided so that the bitstream may convey information relating to such different resolutions. Accordingly, the data may be efficiently coded within the bitstream, depending on the resolution which may vary depending on the content of the picture data coded.

    Encoder, a decoder, and corresponding methods for transform process in video coding

    公开(公告)号:US11589046B2

    公开(公告)日:2023-02-21

    申请号:US17141121

    申请日:2021-01-04

    Abstract: The present disclosure provides methods and devices. A video method of coding implemented by a decoding device, comprising: when a prediction mode of a current coding block is intra prediction, and the current coding block is processed by using Intra sub-partition coding mode, determining whether a width of a current transform block is larger than or equal to a first threshold or not, and whether the width of the current transform block is smaller than or equal to a second threshold or not, the current transform block corresponding to the current coding block; when the width of the current transform block is larger than or equal to the first threshold and the width of the current transform block is smaller than or equal to the second threshold, performing transform process on the current transform block, wherein a transform core based on DST 7 is used on horizontal direction transform.

    Devices and methods for image and video coding

    公开(公告)号:US11563976B2

    公开(公告)日:2023-01-24

    申请号:US17170065

    申请日:2021-02-08

    Abstract: The disclosure relates to a method of decoding implemented by a decoding device, comprising: obtaining a value of a reference line index for a current block; constructing a most probable mode, MPM, list for the current block; obtaining a value of intra-prediction mode index for the current block; when the value of the reference line index is not equal to 0, obtaining an intra prediction mode of the current block according to the MPM list for the current block and the value of the intra-prediction mode index for the current block, wherein the value of the intra-prediction mode index indicates a position that corresponds to the intra prediction mode of the current block among angular intra-prediction modes in the MPM list. The disclosure also relates to a coding apparatus and a non-transitory machine-readable medium.

Patent Agency Ranking