Generating a latent space for a three-dimensional scene

A system comprising:

• a memory component;
• and
• a processing device coupled to the memory component, the processing device to perform operations comprising:
• receiving digital images depicting different views of a scene;
• encoding a tokenized three-dimensional Gaussian splatting representation based on the digital images into a latent space using a machine learning model;
• and
• identifying three-dimensional information related to the scene by decoding the latent space using the machine learning model.

A method comprising:

• receiving, by a processing device, digital images depicting different views of a scene;
• and
• training, by the processing device, a machine learning model to generate a three-dimensional representation based on the scene by:
• encoding a tokenized three-dimensional Gaussian splatting representation based on the digital images using the machine learning model;
• modeling a latent space using the machine learning model based on the tokenized three-dimensional Gaussian splatting representation;
• and
• determining three-dimensional information related to the scene for generating the three-dimensional representation by decoding the latent space using the machine learning model.