| abstract |
The present application provides video coding and decoding methods and apparatuses based on image super-resolution. In the method of the present application, before a video image to be coded or decoded is predicted, super-resolution interpolation processing is performed on the video image to be coded/decoded, amplification and detailed information recovery can be performed on the image to be coded/decoded, and therefore when the image to be coded/decoded is predicted to obtain a prediction block, compared with a method for predicting a video image by means of linear interpolation in the prior art, an original image can be restored more effectively, and the problem that an edge of a prediction block is blurry in the prior art is avoided, thereby enhancing the prediction accuracy of the video image, and further, improving the coding efficiency of the video image. |