Systems and methods for predicting a depth map using diffusion-based modeling

A non-transitory computer-readable medium comprising:

• instructions that when executed by a processor cause the processor to:
• estimate a local vector for an image by combining random noise, an image embedding about the image, and a geometric embedding using a learning model, the local vector having depth information at a pixel-level for the image;
• predict a global vector by combining the image embedding and the geometric embedding at a scene-level by the learning model;
• and
• infer a depth map of the image by combining the local vector and the global vector using a diffusion model.

A method comprising:

• estimating a local vector for an image by combining random noise, an image embedding about the image, and a geometric embedding using a learning model, the local vector having depth information at a pixel-level for the image;
• predicting a global vector by combining the image embedding and the geometric embedding at a scene-level by the learning model;
• and
• inferring a depth map of the image by combining the local vector and the global vector using a diffusion model.