Video frame reconstruction method and device, and terminal device
A technology for video frame and image reconstruction, applied in digital video signal modification, instrument, character and pattern recognition, etc., can solve the problem of low video compression performance, reduce time domain redundancy and improve compression performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] figure 1 The implementation flow of the video frame reconstruction method provided by Embodiment 1 of the present invention is shown. The execution subject of the method may be a terminal device, and the details are as follows:
[0027] In step S101, the reconstructed images of the N-2th frame and the N-1th frame are obtained in the video compression network.
[0028] Optionally, extract the weight parameters of the network corresponding to the N-2 frame and the N-1 frame in the video compression network;
[0029] Further, after encoding and decoding the above weight parameters, the reconstructed weight parameters are generated; wherein, the above codes can be entropy coding schemes such as Shannon coding, Huffman coding or arithmetic coding (arithmetic coding), where without limitation;
[0030] Further, initialize the network corresponding to the above-mentioned N-2th frame and the N-1th frame according to the above-mentioned reconstruction weight parameter; optiona...
Embodiment 2
[0044] figure 2 A structural block diagram of an apparatus for reconstructing a video frame provided by an embodiment of the present invention is shown, and for convenience of description, only parts related to the embodiment of the present invention are shown. The video frame reconstruction device 2 includes: a reconstructed image module 21 , an optical flow module 22 , a predicted frame module 23 , and a reconstructed frame module 24 .
[0045] Wherein, the reconstructed graph module 21 is used to obtain the reconstructed graphs of the N-2 frame and the N-1 frame in the video compression network;
[0046] The optical flow module 22 is used to obtain the optical flow according to the reconstruction images of the N-2th frame and the N-1th frame above;
[0047] The predicted frame module 23 is used to obtain the predicted frame of the Nth frame based on the above-mentioned optical flow and the reconstructed image of the N-1th frame;
[0048] The reconstructed frame module 24...
Embodiment 3
[0063] image 3 It is a schematic diagram of a video frame reconstruction terminal device provided by an embodiment of the present invention. Such as image 3 As shown, the video frame reconstruction terminal device 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and operable on the processor 30, such as a video frame reconstruction program. When the above-mentioned processor 30 executes the above-mentioned computer program 32, the steps in the above-mentioned embodiments of the video frame reconstruction method are realized, for example figure 1 Steps 101 to 104 are shown. Alternatively, when the above-mentioned processor 30 executes the above-mentioned computer program 32, the functions of each module / unit in the above-mentioned device embodiments are realized, for example figure 2 Functions of modules 21 to 24 shown.
[0064] Exemplarily, the above-mentioned computer program 32 can be divided into one or mor...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More