Image-based depth data and localization

A method comprising:

• determining reference data of an environment;
• determining image data from an image sensor associated with a vehicle;
• inputting a portion of the image data to a machine-learned model;
• receiving, from the machine-learned model and based at least in part on the portion of the image data, depth data associated with the environment;
• and
• determining, based at least in part on comparing a portion of the depth data to a portion of the reference data, a location in the environment.

One or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:

• determining reference data of an environment;
• determining image data from an image sensor associated with a vehicle;
• inputting a portion of the image data to a machine-learned model;
• receiving, from the machine-learned model and based at least in part on the portion of the image data, depth data associated with the environment;
• and
• determining, based at least in part on comparing a portion of the depth data to a portion of the reference data, a location in the environment.

A system comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
• determining reference data of an environment;
• determining image data from an image sensor associated with a vehicle;
• inputting a portion of the image data to a machine-learned model;
• receiving, from the machine-learned model and based at least in part on the portion of the image data, depth data associated with the environment;
• and
• determining, based at least in part on comparing a portion of the depth data to a portion of the reference data, a location in the environment.