Low-latency machine learning-based stereo streaming

An apparatus for decoding video data, the apparatus comprising:

• at least one memory;
• and
• at least one processor coupled to the at least one memory, the at least one processor configured to:
• obtain a first reconstructed right-view image of a right view of a scene at a first time step and a first reconstructed left-view image of a left view of the scene at the first time step;
• obtain encoded motion information associated with a compressed right-view image and a compressed left-view image;
• decode the encoded motion information to generate reconstructed motion information;
• and
• warp, using the reconstructed motion information, the first reconstructed right-view image and the first reconstructed left-view image to generate a second reconstructed right-view image of a right view of the scene at a second time step and a second reconstructed left-view image of a left view of the scene at the second time step.