Systems and methods for encoding three-dimensional media content

A computer-implemented system comprising:

• control circuitry configured to:
• access a frame of 3D media content;
• and
• generate encoded data for the frame based at least in part on weights of a trained machine learning model and a data structure,
• wherein, at a first time, the data structure is generated based at least in part on color attributes information of the frame, wherein each element of the data structure encodes a single color,
• wherein to obtain the trained machine learning model, a machine learning model is trained, based at least in part on the frame of 3D media content, to receive as input a coordinate of a voxel of the frame, and to output, at a second time later than the first time, an identifier of a particular element in the data structure having been generated at the first time;
• and
• memory circuitry configured to store the encoded data.

A computer-implemented method, comprising;

• receiving, at a client device, encoded data for a frame of a 3D media content;
• and
• decoding the encoded data and generating for display the frame of the 3D media content, wherein:
• the encoded data is generated based at least in part on weights of a trained machine learning model and a data structure,
• wherein, at a first time, the data structure is generated based at least in part on color attributes information of the frame, wherein each element of the data structure encodes a single color, and
• wherein to obtain the trained machine learning model, a machine learning model is trained, based at least in part on the frame of 3D media content, to receive as input a coordinate of a voxel of the frame, and to output, at a second time later than the first time, an identifier of a particular element in the data structure having been generated at the first time.