Temporally coherent volumetric video

A non-transitory computer-readable medium comprising computer-executable instructions which, when executed by a computing device, cause the computing device to carry out a method for generating a temporally coherent plurality of frames in a volumetric video, the method comprising steps of:

• finding a deformation field configured to transform a source frame of the volumetric video into a target frame of the volumetric video comprising steps of:
• building a texture implicit function for said target frame;
• training a neural network to generate said deformation field between said source frame and said target frame, said texture implicit function for said target frame being a texture matching loss for said neural network;
• and
• applying said deformation field to said source frame, thereby generating a deformed source frame;
• selecting a plurality of frames in said volumetric video;
• selecting a first source frame in said plurality of frames;
• and
• for each frame in said plurality of frames other than said first source frame, repeating the steps of finding said deformed source frame, said finding of said deformed source frame following one of the following paths:
• finding a first deformed source frame from said first source frame;
• and each subsequent source frame being a deformed source frame from a previous pair of frames;
• or
• said each frame in said plurality of frames other than said first source frame being a deformation of said first source frame;
• wherein said neural network is an overfitted neural network that links a single pair of frames comprising said source frame and said target frame.