公开(公告)号：US20240422324A1

公开(公告)日：2024-12-19

申请号：US18819998

申请日：2024-08-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yunying GE ,  Jing WANG ,  Yibo SHI

IPC: H04N19/137 ,  H04N19/169 ,  H04N19/30

Abstract: This application provides a feature domain optical flow determining method and a related device, and relates to the field of video or picture compression technologies based on artificial intelligence (AI). The method specifically includes: obtaining a picture domain optical flow between a current frame and a reference frame; performing multi-scale feature extraction on the reference frame, to obtain M feature maps of the reference frame, where M is an integer greater than or equal to 1; and performing M times of feature domain optical flow estimation based on the M feature maps of the reference frame and the picture domain optical flow between the current frame and the reference frame, to obtain M feature domain optical flows. A feature domain optical flow obtained by using the solutions of this application is more accurate and more stable, thereby improving inter-prediction accuracy.

公开(公告)号：US20240221230A1

公开(公告)日：2024-07-04

申请号：US18604842

申请日：2024-03-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yibo SHI ,  Yunying GE ,  Jing WANG ,  Jue MAO ,  Yin ZHAO ,  Haitao YANG

IPC: G06T9/00

CPC classification number: G06T9/001 ,  G06T9/002

Abstract: This application provides a feature map encoding and decoding method and an apparatus, and relates to the field of artificial intelligence (AI)-based data encoding and decoding technologies. The feature map decoding method includes: obtaining a bitstream of a to-be-decoded feature map, where the to-be-decoded feature map includes a plurality of feature elements; obtaining a first probability estimation result corresponding to each feature element based on the bitstream, where the first probability estimation result includes a first peak probability; determining a set of first feature elements and a set of second feature elements from the plurality of feature elements based on a first threshold and the first peak probability corresponding to each feature element; and obtaining a decoded feature map based on the set of first feature elements and the set of second feature elements. This can improve encoding and decoding performance while reducing encoding and decoding complexity.

公开(公告)号：US20230396810A1

公开(公告)日：2023-12-07

申请号：US18453933

申请日：2023-08-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yunying GE ,  Jing WANG ,  Yibo SHI ,  Shangyin GAO

IPC: H04N19/91 ,  H04N19/184 ,  G06V10/771

CPC classification number: H04N19/91 ,  H04N19/184 ,  G06V10/771

Abstract: This application provides an audio/video or picture compression method and apparatus, which relates to the field of artificial intelligence (AI)-based audio/video or picture compression technologies, and to the field of neural network-based audio/video or picture compression technologies. The method includes: transforming a raw audio/video or picture to feature space through a multilayer convolution operation, extracting features of different layers in the feature space, outputting rounded feature signals of the different layers, predicting probability distribution of shallow feature signals by using deep feature signals or entropy estimation results, and performing entropy encoding on the rounded feature signals. In this application, signal correlation between different layers is utilized. In this way, audio/video or picture compression performance can be improved.