Monocular Depth Prediction

Closed weights Stanford University 1.5M parameters December 2005

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Stanford University
Organisation type
Academia
Country
United States of America
Published
5 December 2005
Authors
Ashutosh Saxena, Sung H. Chung, and Andrew Y. Ng

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Miscellaneous image analysis
Approach
Supervised

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
1.5M

"In detail, we use different parameters (θr, σ1r, σ2r) for each row in the image, because the images we consider are taken from a horizontally mounted camera, and thus different rows of the image have different statistical properties." "We collected a total of 425 image+depthmap pairs, with an image resolution of 1704x2272 and a depthmap resolution of 86x107" The dimensionality of each parameter set isn't totally clear, but from equation (1) it seems like θ is the same length as the absolute de…

Training data
2,933,137 tokens

"We collected a total of 425 image+depthmap pairs, with an image resolution of 1704x2272 and a depthmap resolution of 86x107. In the experimental results reported here, 75% of the images/depthmaps were used for training, and the remaining 25% for hold-out testing" It seems like they do predictions over the dense values in the depthmap, so 86 * 107 * 425 * 0.75 = 2,933,137

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Speculative
Citations
1,417

Sources

Where this record came from and when it was last checked.

Reference
Learning Depth from Single Monocular Images
Last updated
28 November 2025

What the numbers mean

About this model

Monocular Depth Prediction was published by Stanford University, in the country recorded as United States of America, during December 2005. The category the publisher falls under is academia.

It works in the domain of Vision, and is recorded as performing the task of miscellaneous image analysis.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

It was trained on a corpus of about 2,933,137 tokens of text.

Answers

Monocular Depth Prediction — common questions

01

Monocular Depth Prediction— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

02

Monocular Depth Prediction— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

03

Monocular Depth Prediction— how many parameters does it have?

It has a parameter count of 1.5M. "In detail, we use different parameters (θr, σ1r, σ2r) for each row in the image, because the images we consider are taken from a horizontally mounted camera, and thus different rows of the image have different statistical properties." "We collected a total of 425 image+depthmap pairs, with an image resolution of 1704x2272 and a depthmap resolution of 86x107" The dimensionality of each parameter set isn't totally clear, but from equation (1) it seems like θ is the same length as the absolute depth input features (646) and σ1 and σ2 are scalar. If so, then we should have: 2272 * (646 + 1 + 1) = 1,472,256 parameters. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

04

Monocular Depth Prediction— who created it?

It was published by Stanford University, based in United States of America, an organisation categorised as academia.

05

Monocular Depth Prediction— when was it released?

It was published in December 2005. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

Monocular Depth Prediction— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of miscellaneous image analysis. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.