Encoding three-dimensional media content

A computer implemented system, comprising:

• control circuitry configured to:
• access a first frame of three-dimensional (3D) media content;
• and
• generate first encoded data for the first frame based at least in part on:
• a first data structure, wherein, at a first time, the first data structure is generated based at least in part on color attributes information of the first frame;
• and
• one or more first weights of one or more first layers of a first machine learning model, wherein the first machine learning model is configured to, at a second time later than the first time, output an identifier of an element of the first data structure based at least in part on receiving as input geometry information for a portion of the first frame;
• and
• perform at least one of storing the first encoded data or transmitting the first encoded data;
• generate second encoded data for a second frame of the 3D media content based at least in part on:
• one or more second weights of one or more second layers of a second machine learning model, wherein the one or more second weights are determined based at least in part on the one or more first weights;
• and
• perform at least one of storing the second encoded data or transmitting the second encoded data.