Image processing method and related device
An image processing method and apparatus are provided. The method includes: obtaining an image; performing feature extraction on the image to obtain at least one first feature map, wherein the at least one first feature map includes N first feature values, and N is a positive integer; obtaining a target compression bit rate which corresponds to M target gain values, each target gain value corresponds to one first feature value, and M is a positive integer less than or equal to N; respectively processing corresponding first feature values based on the M target gain values to obtain M second feature values; and performing quantization and entropy encoding on at least one processed first feature map to obtain encoded data, wherein the at least one processed first feature map includes the M second feature values. According to the application, compression bit rate control is implemented in a same compression model.
1. An image processing method applied to an image processing device comprising one or more processors, the method comprising:
obtaining a first image;
performing feature extraction on the first image to obtain at least one first feature map, wherein the at least one first feature map comprises N first feature values, and N is a positive integer;
obtaining a target compression bit rate;
determining, based on a target mapping relationship, M target gain values corresponding to the target compression bit rate, wherein the target mapping relationship indicates an association relationship between a compression bit rate and M target gain values, each target gain value of the M target gain values corresponds to a first feature value of the N first feature values, and M is a positive integer less than or equal to N;
respectively processing corresponding first feature values based on the M target gain values to obtain M second feature values; and
performing quantization and entropy encoding on at least one processed first feature map to obtain encoded data, wherein the at least one processed first feature map comprises the M second feature values;
wherein the target mapping relationship comprises a target function mapping relationship, and based on an input of the target function mapping relationship comprising the target compression bit rate, an output of the target function mapping relationship comprises the M target gain values.
2. The method according to claim 1 , wherein information entropy of quantized data obtained by quantizing the at least one processed first feature map meets a preset condition, and the preset condition is related to the target compression bit rate.
3. The method according to claim 2 , wherein the preset condition comprises at least:
a larger target compression bit rate indicates larger information entropy of the quantized data.
4. The method according to claim 1 , wherein a difference between a compression bit rate corresponding to the encoded data and the target compression bit rate falls within a preset range.
5. The method according to claim 1 , wherein the M second feature values are obtained by separately performing a multiplication operation on the M target gain values and the corresponding first feature values.
6. The method according to claim 1 , wherein the at least one first feature map comprises a first target feature map, the first target feature map comprises P first feature values, all of the P first feature values correspond to a same target gain value of the M target gain values, and P is a positive integer less than or equal to M.
7. The method according to claim 1 , wherein the target compression bit rate is greater than a first compression bit rate and less than a second compression bit rate, the first compression bit rate corresponds to M first gain values, the second compression bit rate corresponds to M second gain values, and the M target gain values are obtained by performing an interpolation operation on the M first gain values and the M second gain values.
8. The method according to claim 1 , wherein the first image comprises a target object, and M first feature values are feature values that are in the at least one first feature map and that correspond to the target object.
9. The method according to claim 1 , wherein each target gain value of the M target gain values corresponds to one reverse gain value, the reverse gain value is used to process a feature value obtained in a decoding process of the encoded data, and a product of each target gain value of the M target gain values and the corresponding reverse gain value falls within a preset range.
10. An image processing method applied to an image processing device comprising one or more processors, the method comprising:
obtaining encoded data;
performing entropy decoding on the encoded data to obtain at least one second feature map, wherein the at least one second feature map comprises N third feature values, and N is a positive integer;
obtaining a target compression bit rate;
determining, based on a target mapping relationship, M target reverse gain values corresponding to the target compression bit rate, wherein the target mapping relationship indicates an association relationship between a compression bit rate and a reverse gain vector, wherein each target reverse gain value of the M target reverse gain values corresponds to a third feature value of the N third feature values, and M is a positive integer less than or equal to N;
respectively processing corresponding third feature values based on the M target reverse gain values, to obtain M fourth feature values; and
performing image reconstruction on at least one processed second feature map to obtain a second image, wherein the at least one processed second feature map comprises the M fourth feature values,
wherein the target mapping relationship comprises a target function mapping relationship, and based on an input of the target function mapping relationship comprising the target compression bit rate, an output of the target function mapping relationship comprises the M target reverse gain values.
11. The method according to claim 10 , wherein the M fourth feature values are obtained by separately performing a multiplication operation on the M target reverse gain values and the corresponding third feature values.
12. The method according to claim 10 , wherein the at least one second feature map comprises a second target feature map, the second target feature map comprises P third feature values, all of the P third feature values correspond to a same target reverse gain value of the M target reverse gain values, and P is a positive integer less than or equal to M.
13. The method according to claim 10 , wherein the second image comprises a target object, and M third feature values are feature values that are in the at least one second feature map and that correspond to the target object.
14. The method according to claim 10 , wherein the target compression bit rate is greater than a first compression bit rate and less than a second compression bit rate, the first compression bit rate corresponds to M first reverse gain values, the second compression bit rate corresponds to M second reverse gain values, and the M target reverse gain values are obtained by performing an interpolation operation on the M first reverse gain values and the M second reverse gain values.
15. A device, comprising:
one or more processors;
a non-transitory computer-readable storage medium coupled to the one or more processors and storing instructions that, upon being executed by the one or more processors, cause the device to perform operations comprising:
obtaining a first image;
performing feature extraction on the first image to obtain at least one first feature map, wherein the at least one first feature map comprises N first feature values, and N is a positive integer;
obtaining a target compression bit rate;
determining, based on a target mapping relationship, M target gain values corresponding to the target compression bit rate, wherein the target mapping relationship indicates an association relationship between a compression bit rate and the M target gain values, each target gain value of the M target gain values corresponds to a first feature value of the N first feature values, and M is a positive integer less than or equal to N;
respectively processing corresponding first feature values based on the M target gain values to obtain M second feature values; and
performing quantization and entropy encoding on at least one processed first feature map to obtain encoded data, wherein the at least one processed first feature map comprises the M second feature values;
wherein the target mapping relationship comprises a target function mapping relationship, and based on an input of the target function mapping relationship comprising the target compression bit rate, an output of the target function mapping relationship comprises the M target gain values.
16. The device according to claim 15 , wherein the M second feature values are obtained by separately performing a multiplication operation on the M target gain values and the corresponding first feature values.
17. The device according to claim 15 , wherein the at least one first feature map comprises a first target feature map, the first target feature map comprises P first feature values, all of the P first feature values correspond to a same target gain value of the M target gain values, and P is a positive integer less than or equal to M.