Reproducible learning-based point cloud coding

An apparatus comprising:

• a processor;
• and
• a memory storing instructions operative, when executed by the processor, to cause the apparatus to:
• decode a motion feature from a motion bitstream;
• obtain one or more reference point cloud frames;
• determine a predicted feature based on the motion feature and the one or more reference point cloud frames;
• obtain a feature safeguard bitstream;
• decode feature safeguard information from the feature safeguard bitstream;
• decode a first feature representing an occupancy of a child level based on the feature safeguard information;
• determine a second feature based on the first feature and the predicted feature;
• and
• decode a tree voxel occupancy status of the child level via the second feature.

A method comprising:

• determining a motion feature from a current point cloud and one or more reference point cloud frames;
• determining a predicted feature based on the motion feature;
• encoding the motion feature into a motion bitstream;
• determining a first feature representing the occupancy of a child level;
• determining a second feature based on the first feature and the predicted feature;
• performing a protection mechanism to obtain a feature safeguard information and a safeguarded second feature;
• encoding the feature safeguard information into a feature safeguard bitstream;
• and
• encoding the safeguarded second feature into the feature safeguard bitstream.