Entropy coding/decoding method and device
An entropy encoding and encoding technology, applied in the field of entropy encoding/decoding methods and devices, can solve problems such as video size becoming a problem
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0345] Figure 13An exemplary flow chart of the entropy encoding method of the present application, such as Figure 13 As shown, x represents the original value of the image block. In the video encoder, x is encoded by an encoder based on the hybrid coding framework to obtain the first coded stream corresponding to the basic layer information, and the first coded stream is then decoded by a decoder based on the hybrid decoding framework to obtain the reconstruction of the image block value xc. The video encoder inputs the reconstruction value xc of the image block into the neural network to obtain K sets of probability values. optional, such as Figure 14 As shown, the video encoder can first input the reconstruction value xc of the image block into Encoder2 for feature extraction before inputting the reconstruction value xc of the image block into the neural network, and then input the feature value corresponding to the reconstruction value xc of the image block into the n...
Embodiment 2
[0349] Figure 15 An exemplary flow chart of the entropy encoding method of the present application, such as Figure 15 As shown, x represents the original value of the image block. The difference from the first implementation is that the video encoder and decoder input the residual value Δx of the image block into the neural network, that is, in this embodiment, K groups of probability values are obtained based on the residual value Δx of the image block.
Embodiment 3
[0351] Figure 16 An exemplary flow chart of the entropy encoding method of the present application, such as Figure 16 As shown, x represents the original value of the image block. The difference from Implementation 1 is that the video encoder and decoder input both the residual value Δx of the image block and the reconstruction value xc of the image block into the neural network, that is, in this embodiment, it is based on the residual value Δx of the image block and the reconstruction value xc of the image block The reconstructed value xc obtains K sets of probability values.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


