Neural-network media compression using quantized entropy coding distribution parameters

1. A method of coding media data, the method comprising:

determining a probability distribution function parameter for a data element of a data stream coded by a neural-based media compression technique, wherein the probability distribution function parameter is based on a distribution of the data stream wherein the probability distribution function parameter is optimized for quantization,

determining a code vector based on the probability distribution function parameter; and

entropy coding the data element using the code vector.

2. The method of claim 1 , further comprising:

quantizing the probability distribution function parameter prior to determining the code vector.

3. The method of claim 1 , wherein the probability distribution function parameter is u, the standard deviation of the probability distribution function is σ, a minimum standard deviation is σ min , a maximum standard deviation is σ max , and wherein the relationship between u and σ is defined as: σ=T u→σ (u)=T λ→σ (T u→λ (u)), where T λ→σ (λ)=exp(λ ln(σ max /σ min )+ln(σ min )), where functions T are defined according to an algorithm that measures coding redundancy or defined by solving an ordinary differential equation.

4. The method of claim 1 , wherein the probability distribution function parameter is a function of a standard deviation of a probability distribution function of the data stream.

5. The method of claim 1 , further comprising:

generating the data element using the neural-based compression technique; and

quantizing the data element to create a quantized data element,

wherein entropy coding the data element using the code vector comprises entropy encoding the quantized data element using the code vector.

6. The method of claim 5 , wherein generating the data element using the neural-based compression technique comprises:

processing an image or video picture using an image analysis neural network to generate the data element.

7. The method of claim 6 , further comprising:

capturing the image or video picture using a camera.

8. The method of claim 1 , wherein entropy coding the data element using the code vector comprises entropy decoding an encoded data element using the code vector to create a quantized data element, the method further comprising:

dequantizing the quantized data element to create a reconstructed data element.

9. The method of claim 8 , further comprising:

processing the reconstructed data element using an image synthesis neural network to reconstruct an image or video picture.

10. The method of claim 9 , further comprising:

displaying the image or the video picture.

11. An apparatus configured to code media data, the apparatus comprising:

a memory; and

one or more processors in communication with the memory, the one or more processors configured to:

determine a probability distribution function parameter for a data element of a data stream coded by a neural-based media compression technique, wherein the probability distribution function parameter is based on a distribution of the data stream wherein the probability distribution function parameter is optimized for quantization;

determine a code vector based on the probability distribution function parameter; and

entropy code the data element using the code vector.

12. The apparatus of claim 11 , wherein the one or more processors are further configured to:

quantize the probability distribution function parameter prior to determining the code vector.

13. The apparatus of claim 11 , wherein the probability distribution function parameter is u, the standard deviation of the probability distribution function is σ, a minimum standard deviation is σ min , a maximum standard deviation is σ max , and wherein the relationship between u and σ is defined as: σ=T u→σ (u)=T λ→σ (T u→λ (u)), where T λ→σ (λ)=exp(λ ln(σ max /σ min )+ln(σ min )), where functions T are defined according to an algorithm that measures coding redundancy or defined by solving an ordinary differential equation.

14. The apparatus of claim 11 , wherein the probability distribution function parameter is a function of a standard deviation of a probability distribution function of the data stream.

15. The apparatus of claim 11 , wherein the one or more processors are further configured to:

generate the data element using the neural-based compression technique; and

quantize the data element to create a quantized data element,

wherein entropy coding the data element using the code vector comprises entropy encoding the quantized data element using the code vector.

16. The apparatus of claim 15 , wherein to generate the data element using the neural-based compression technique, the one or more processors are further configured to:

process an image or video picture using an image analysis neural network to generate the data element.

17. The apparatus of claim 16 , further comprising:

a camera configured to capture the image or video picture.

18. The apparatus of claim 11 , wherein entropy coding the data element using the code vector comprises entropy decoding an encoded data element using the code vector to create a quantized data element, and wherein the one or more processors are further configured to:

dequantize the quantized data element to create a reconstructed data element.

19. The apparatus of claim 18 , wherein the one or more processors are further configured to:

process the reconstructed data element using an image synthesis neural network to reconstruct an image or video picture.

20. The apparatus of claim 19 , further comprising:

a display configured to display the image or video picture.