Systems and methods for encoding three-dimensional media content

1. A computer-implemented method, comprising;

accessing a first frame of 3D media content;

at a first time, generating a data structure for the first frame based on color attributes information of the first frame, wherein each element of the data structure encodes a single color;

training a machine learning model based on the first frame of 3D media content, wherein the machine learning model is trained to receive as input a coordinate of a voxel of the first frame, and to output, at a second time later than the first time, an identifier of a particular element in the generated data structure having been generated at the first time; and

generating encoded data for the first frame based at least in part on weights of the trained machine learning model and the generated data structure.

2. The method of claim 1 , further comprising generating the data structure by applying vector quantization to the color attributes information of the first frame, and wherein the data structure is a color table, and the particular element is a row or column of the color table.

3. The method of claim 2 , wherein applying the vector quantization comprises applying K-means clustering to the color attributes information of the first frame.

4. The method of claim 1 , wherein generating the data structure comprises applying vector quantization to color attributes of a plurality of sequential frames of the 3D media content, the plurality of sequential frames including the first frame; and

the method further comprises generating a group of pictures (GOP) comprising the plurality of sequential frames, wherein the GOP is associated with the data structure.

5. A computer-implemented method, comprising;

accessing a first frame of 3D media content;

at a first time, generating a data structure for the first frame based on color attributes information of the first frame, wherein each element of the data structure encodes a single color;

training a machine learning model based on the first frame of 3D media content, wherein the machine learning model is trained to receive as input a coordinate of a voxel of the first frame, and to output, at a second time later than the first time, an identifier of a particular element in the generated data structure having been generated at the first time, wherein training the machine learning model comprises:

causing the machine learning model to learn weights for a plurality of layers of the machine learning model in association with receiving input of the first frame by:

adjusting the weights based on a comparison between the output of the machine learning model and color attributes information of the first frame, wherein the adjusting is repeated until a certain performance level is achieved; and

generating encoded data for the first frame based at least in part on the weights of the trained machine learning model and the generated data structure.

6. The method of claim 5 , wherein the 3D media content comprises a second frame sequential to the first frame in the 3D media content, and the method further comprises:

generating encoded data for the second frame by:

re-using the weights learned by the machine learning model for the plurality of layers in association with receiving input of the first frame; and

updating the machine learning model by adding one or more additional layers to the plurality of layers and learning weights associated with the one or more additional layers in association with receiving input of the second frame, wherein the updating comprises adjusting the weights associated with the one or more additional layers based on a comparison between the output of the machine learning model and color attributes information of the second frame, and the updating is repeated until a certain performance level is achieved.

7. The method of claim 1 , further comprising:

transmitting the encoded data to a client device, the encoded data comprising an indication of the coordinate of the voxel of the first frame, the weights of the trained machine learning model, and the generated data structure.

8. The method of claim 7 , wherein the transmitting of the encoded data causes the client device to:

generate the trained machine learning model using the received weights; and

determine color attributes information for the first frame by:

inputting the coordinate of the voxel of the first frame into the trained machine learning model which outputs an identifier of a particular row in the generated data structure; and

using the received data structure and the output identifier to determine the color attributes information for the first frame; and

generate for display the first frame of the 3D media content based on the determined color attributes information.

9. The method of claim 1 , wherein the machine learning model comprises a softmax layer configured to output probabilities that respective candidate identifiers in the data structure correspond to color attributes of the input coordinate, and wherein a size of the softmax layer is based on a size of the data structure.

10. The method of claim 1 , further comprising:

preprocessing the input to the machine learning model using a Fourier embedding layer.

11. A computer-implemented system, comprising:

control circuitry configured to:

access a first frame of 3D media content;

at a first time, generate a data structure for the first frame based on color attributes information of the first frame, wherein each element of the data structure encodes a single color;

train a machine learning model based on the first frame of 3D media content, wherein the machine learning model is trained to receive as input a coordinate of a voxel of the first frame and output, at a second time later than the first time, an identifier of a particular element in the generated data structure having been generated at the first time; and

generate encoded data for the first frame based at least in part on weights of the trained machine learning model and the generated data structure; and

memory circuitry configured to store the encoded data.

12. The system of claim 11 , wherein the control circuitry is configured to generate the data structure by applying vector quantization to the color attributes information of the first frame, and wherein the data structure is a color table, and the particular element is a row or column of the color table.

13. The system of claim 12 , wherein the control circuitry is configured to apply the vector quantization by applying K-means clustering to the color attributes information of the first frame.

14. The system of claim 11 , wherein the control circuitry is configured to generate the data structure by applying vector quantization to color attributes of a plurality of sequential frames of the 3D media content, the plurality of sequential frames including the first frame; and

wherein the control circuitry is further configured to generate a group of pictures (GOP) comprising the plurality of sequential frames, wherein the GOP is associated with the data structure.

15. The system of claim 11 , wherein the control circuitry is configured to train the machine learning model by:

causing the machine learning model to learn the weights for a plurality of layers of the machine learning model in association with receiving input of the first frame by:

adjusting the weights based on a comparison between the output of the machine learning model and color attributes information of the first frame, and the control circuitry is configured to repeat the adjusting until a certain performance level is achieved.

16. The system of claim 15 , wherein the 3D media content comprises a second frame sequential to the first frame in the 3D media content, and the control circuitry is further configured to:

generate encoded data for the second frame by:

re-using the weights learned by the machine learning model for the plurality of layers in association with receiving input of the first frame; and

updating the machine learning model by adding one or more additional layers to the plurality of layers and learning weights associated with the one or more additional layers in association with receiving input of the second frame, wherein the control circuitry is configured to perform the updating by adjusting the weights associated with the one or more additional layers based on a comparison between the output of the machine learning model and color attributes information of the second frame, and the control circuitry is configured to repeat the updating until a certain performance level is achieved.

17. The system of claim 11 , wherein the control circuitry is further configured to:

transmit the encoded data to a client device, the encoded data comprising an indication of the coordinate of the voxel of the first frame, the weights of the trained machine learning model, and the generated data structure.

18. The system of claim 17 , wherein the control circuitry is further configured to transmit the encoded data to cause the client device to:

generate the trained machine learning model using the received weights; and

determine color attributes information for the first frame by:

inputting the coordinate of the voxel of the first frame into the trained machine learning model which outputs an identifier of a particular row in the generated data structure; and

using the received data structure and the output identifier to determine the color attributes information for the first frame; and

generate for display the first frame of the 3D media content based on the determined color attributes information.

19. The system of claim 11 , wherein the machine learning model comprises a softmax layer configured to output probabilities that respective candidate identifiers in the data structure correspond to color attributes of the input coordinate, and wherein a size of the softmax layer is based on a size of the data structure.

20. The system of claim 11 , wherein the control circuitry is further configured to:

preprocess the input to the machine learning model using a Fourier embedding layer.