Video decoding method, device, electronic device, storage medium and computer program product
CN119865612BActive Publication Date: 2026-08-28CHINA MOBILE COMM LTD RES INST +1
Patent Information
- Application Number
- CN202411865528.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2026-08-28
- Estimated Expiration
- 2044-12-17
AI Technical Summary
Technical Problem
而当需要同时进行人类视觉任务和机器视觉任务时,现有的统一框架并不成熟,在视频分析时的比特率仍然会显著增加
Benefits of technology
[0061]本申请实施例提供的一种视频解码方法、装置、电子设备、存储介质及计算机程序产品中,在视频解码端进行视频解码时,首先基于视频的第一码流和第二码流进行帧内解码来生成参考帧列表,然后将参考帧列表进行更新后进行帧间解码并重构当前帧对应的原始帧;该第一码流包括对该视频的一个或多个原始帧进行帧内编码形成的码流;该第二码流包括对该一个或多个原始帧进行帧内编码和帧间编码形成的码流;具体地,更新参考帧列表之前,调用第一DNN模型对从该参考帧列表中选取的当前帧对应的第一参考帧和第二参考帧进行处理,得到当前帧对应的第一预测帧;更新参考帧列表包括:用该第一预测帧替换该参考帧列表中的第三参考帧,该第三参考帧表征与该当前帧的POC差异最大的参考帧。基于第一DNN模型可以对上述参考帧列表进行更新,因此预测图形块的形状可不受限制,不需要启用额外的块形状,也就不需要额外的标志位,所以可在视频分析任务中降低传输的比特流,显著提高视频解码的效率。此外,在执行目标检测任务的情况下,解码端对视频的第一码流进行解码,在执行视频重建任务的情况下,解码端对该视频的该第一码流和第二码流进行解码,可以完成机器视觉和人类视觉任务的切换,既能保证目标检测的效率,又可以满足高质量的视频重建的需求。
✦ Generated by Eureka AI based on patent content.
Smart Images

Figure CN119865612B_ABST
Abstract
The application discloses a video decoding method, device, electronic equipment, storage medium and computer program product, wherein the video decoding method comprises: performing intra decoding based on a first code stream and a second code stream of a video to generate a reference frame list; calling a first deep neural network (DNN) model to process a first reference frame and a second reference frame corresponding to a current frame selected from the reference frame list to obtain a first prediction frame corresponding to the current frame; updating the reference frame list, wherein the updating the reference frame list comprises: replacing a third reference frame in the reference frame list with the first prediction frame, the third reference frame representing a reference frame with the largest picture order count (POC) difference from the current frame; based on the updated reference frame list, generating a second prediction frame corresponding to the current frame, and combining the second prediction frame and residual information decoded from the second code stream to reconstruct an original frame corresponding to the current frame.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Video compression processing method and device, storage medium and electronic equipment
CN111263161A
Video processing method and device
CN115499634A