Image coding and decoding method and system
An image encoding and image decoding technology, applied in the field of image recognition, can solve the problems of increased computational complexity, low compression performance, and exponential increase in the amount of calculations, so as to reduce the amount of video memory and calculations, reduce the number of channels and numbers, The effect of the best compression effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0058] see figure 1 and figure 2 , figure 1 is a flowchart of an image encoding method provided by the present invention, figure 2 It is an overall frame diagram of an image coding method and an image decoding method provided by the present invention. It should be noted that the image coding in the embodiment of the present invention is not limited to figure 1 The steps and sequence in the flow chart are shown. According to different requirements, the steps in the flow chart can be added, removed or changed in order.
[0059] Such as figure 1 and figure 2 As shown, the image coding method provided by the present invention includes the following steps:
[0060] S10. Input the original picture as an input image to a lossy coding network, and output an initial feature map corresponding to the original picture through the lossy coding network.
[0061] Such as figure 2 As shown, a coding model is built and trained to obtain a well-trained coding model. The coding model ...
Embodiment 2
[0105] The present invention also provides an image decoding method, such as Figure 5 As shown, the image decoding method includes the following steps:
[0106] The decoding model includes lossless decoding network, lossy decoding network and post-enhancement network. S001. Input the intermediate file to be decompressed into the lossless decoding network, and output the initial quantization feature map through the lossless decoding network; wherein, the intermediate file is the intermediate file obtained in the above step S40.
[0107] Such as figure 2 , build a decoding model, and train it to obtain a trained decoding model, the trained decoding model includes a lossless decoding network, a lossy decoding network and a post-enhancement network. Wherein, the structure and parameters of the lossless decoding network are the same as those of the lossless encoding network in Embodiment 1. The lossless decoding network includes a probabilistic decoding module AD and a priori ...
Embodiment 3
[0133] Based on the above image encoding and decoding methods, the present invention also provides a corresponding system, such as Figure 9 As shown, the system includes a sending terminal 800 and a receiving terminal 900. For the sending terminal 800, the sending terminal processor 12 is connected to the sending terminal memory 11 connected to the sending terminal processor 12, and the sending terminal memory 11 stores and an image coding program that can run on the sending terminal processor 12; for the receiving terminal 900, the receiving terminal 900 includes a receiving terminal processor 112 and a receiving terminal memory 111 connected to the receiving terminal processor 112, the The receiving terminal memory 111 stores an image decoding program that can run on the receiving terminal processor 112 . Figure 9 Only some components of the system are shown, but it is understood that implementation of all illustrated components is not required and that more or fewer compo...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


