Image transmission method and apparatus

1. An image transmission method, wherein the method comprises:

converting a first high-resolution image into a first low-resolution image, wherein first resolution of the first high-resolution image is higher than second resolution of the first low-resolution image;

encoding the first low-resolution image to obtain a first bitstream;

obtaining a second high-resolution image, wherein a third resolution of the second high-resolution image is higher than the second resolution, and the second high-resolution image comprises high-frequency information of the first high-resolution image and excludes low-frequency information of the first high-resolution image;

obtaining an image residual between the first high-resolution image and the second high-resolution image, wherein the image residual is used to reflect the low-frequency information;

encoding the image residual to obtain a second bitstream; and

sending the first bitstream and the second bitstream.

2. The method according to claim 1 , wherein the high-frequency information is image detail information and the low-frequency information is image outline information.

3. The method according to claim 1 , wherein the obtaining a second high-resolution image comprises:

decoding the first bitstream to obtain a second low-resolution image; and

reconstructing the second high-resolution image by using the second low-resolution image.

4. The method according to claim 3 , wherein the reconstructing the second high-resolution image by using the second low-resolution image comprises:

reconstructing the second high-resolution image by using the second low-resolution image and a neural network.

5. The method according to claim 1 , wherein the first resolution and the third resolution are the same; and the obtaining an image residual between the first high-resolution image and the second high-resolution image comprises:

subtracting a pixel value of a first pixel in the first high-resolution image from a pixel value of a second pixel in the second high-resolution image corresponding to the first pixel, to obtain a first pixel residual in the image residual.

6. The method according to claim 1 , wherein the method is applied to video transmission, and the first high-resolution image is a frame of image in a video.

7. An image transmission method, wherein the method comprises:

receiving a first bitstream and a second bitstream;

decoding the first bitstream to obtain a second low-resolution image;

reconstructing a second high-resolution image by using the second low-resolution image, wherein first resolution of the second high-resolution image is higher than second resolution of the second low-resolution image, and the second high-resolution image comprises high-frequency information of a first high-resolution image and excludes low-frequency information of the first high-resolution image;

decoding the second bitstream to obtain an image residual between the first high-resolution image and the second high-resolution image, wherein the image residual is used to reflect the low-frequency information; and

combining the second high-resolution image and the image residual to obtain a third high-resolution image.

8. The method according to claim 7 , wherein the high-frequency information is image detail information and the low-frequency information is image outline information.

9. The method according to claim 7 , wherein the reconstructing a second high-resolution image by using the second low-resolution image comprises:

reconstructing the second high-resolution image by using the second low-resolution image and a neural network.

10. The method according to claim 7 , wherein the combining the second high-resolution image and the image residual to obtain a third high-resolution image comprises:

adding a pixel value of a second pixel in the second high-resolution image to a pixel residual in the image residual corresponding to the second pixel, to obtain a third pixel in the third high-resolution image corresponding to the second pixel.

11. The method according to claim 7 , wherein the method is applied to video transmission, and the first high-resolution image is a frame of image in a video.

12. A transmission apparatus, wherein the apparatus comprises: a processor system and a memory, wherein the memory is configured to store computer executable program code, and the program code includes instructions executed by the processor system to enable the transmission device to perform an image transmission method, comprising:

converting a first high-resolution image into a first low-resolution image, wherein first resolution of the first high-resolution image is higher than second resolution of the first low-resolution image;

encoding the first low-resolution image to obtain a first bitstream;

obtaining a second high-resolution image, wherein third resolution of the second high-resolution image is higher than the second resolution, and the second high-resolution image comprises high-frequency information of the first high-resolution image and excludes low-frequency information of the first high-resolution image;

obtaining an image residual between the first high-resolution image and the second high-resolution image, wherein the image residual is used to reflect the low-frequency information;

encoding the image residual to obtain a second bitstream; and

sending the first bitstream and the second bitstream.

13. The transmission apparatus according to claim 12 , wherein the high-frequency information is image detail information and the low-frequency information is image outline information.

14. The transmission apparatus according to claim 12 , wherein the obtaining a second high-resolution image comprises:

decoding the first bitstream to obtain a second low-resolution image; and

reconstructing the second high-resolution image by using the second low-resolution image.

15. The transmission apparatus according to claim 14 , wherein the reconstructing the second high-resolution image by using the second low-resolution image comprises:

reconstructing the second high-resolution image by using the second low-resolution image and a neural network.

16. The transmission apparatus according to claim 12 , wherein the first resolution and the third resolution are the same; and the obtaining an image residual between the first high-resolution image and the second high-resolution image comprises:

subtracting a pixel value of a first pixel in the first high-resolution image from a pixel value of a second pixel in the second high-resolution image corresponding to the first pixel, to obtain a first pixel residual in the image residual.

17. A transmission apparatus, wherein the apparatus comprises: a processor system and a memory, wherein the memory is configured to store computer executable program code, and the program code includes instructions executed by the processor system to enable the transmission device to perform an image transmission method, comprising:

receiving a first bitstream and a second bitstream;

decoding the first bitstream to obtain a second low-resolution image;

reconstructing a second high-resolution image by using the second low-resolution image, wherein first resolution of the second high-resolution image is higher than second resolution of the second low-resolution image, and the second high-resolution image comprises high-frequency information of a first high-resolution image and excludes low-frequency information of the first high-resolution image;

decoding the second bitstream to obtain an image residual between the first high-resolution image and the second high-resolution image, wherein the image residual is used to reflect the low-frequency information; and

combining the second high-resolution image and the image residual to obtain a third high-resolution image.

18. The transmission apparatus according to claim 17 , wherein the high-frequency information is image detail information and the low-frequency information is image outline information.

19. The transmission apparatus according to claim 17 , wherein the reconstructing a second high-resolution image by using the second low-resolution image comprises:

reconstructing the second high-resolution image by using the second low-resolution image and a neural network.

20. The transmission apparatus according to claim 17 , wherein the combining the second high-resolution image and the image residual to obtain a third high-resolution image comprises:

adding a pixel value of a second pixel in the second high-resolution image to a pixel residual in the image residual corresponding to the second pixel, to obtain a third pixel in the third high-resolution image corresponding to the second pixel.