# Depth Estimation

> Working out how far away each part of a photo is. It makes a depth map.

**Field:** Artificial Intelligence  
**Category:** Robotics & Vision  
**Also known as:** Monocular Depth Estimation, Depth Map, Depth Prediction

## Think of it like

It is like guessing how far away a tree is just by looking. Small and hazy means far.

## Definition

Depth estimation works out how far away each part of a picture is. The answer is a depth map, an image where each pixel holds a distance. With two cameras side by side, the model compares the views, as your two eyes do. With one camera, a model learns clues like size, shade and blur. One camera is cheap, but its guesses are less exact than lidar.

## Example

Lucy's phone blurs the background in portrait photos. A depth model guesses which pixels are her and which are the wall behind her.

## Why it matters

Robots need distance, not just a picture, to grab things. A depth map gives it from a cheap camera.

## Common mistake

Trusting a single-camera depth map as exact. It is a learned guess, and glass, mirrors and plain walls can fool it.

## Three principles

- **Distance per pixel.** The output is a depth map.
- **Two eyes or one.** Compare two views, or learn the clues.
- **A guess, not a tape.** Lidar measures more exactly.

## Related terms

- [Light Detection and Ranging (LiDAR)](https://learn.benibix.com/term/ai/lidar)
- [Point Cloud](https://learn.benibix.com/term/ai/point-cloud)
- [Computer Vision](https://learn.benibix.com/term/ai/computer-vision)
- [Sensor Fusion](https://learn.benibix.com/term/ai/sensor-fusion)
- [Image Segmentation](https://learn.benibix.com/term/ai/image-segmentation)

## Told apart from

- [LiDAR vs Depth Estimation](https://learn.benibix.com/compare/lidar-vs-depth-estimation): People think only lidar can tell how far away things are, and that is not so. Lidar times flashes of light, so it is right to a few centimetres, even in the dark. Depth estimation guesses distance from camera pictures. It uses two views, or clues like size and shade. It is cheaper and sees colour, but its guesses are rougher.

![Three panels. Left: a lidar sends a flash of light to a wall and the echo comes back. Middle: a wall, a floor and a chair drawn only as dots, a point cloud. Right: a camera photo beside its depth map, where the near box and the far wall get different shades.](https://learn.benibix.com/diagrams/ai6-3d-sensing.svg)

---

Source: https://learn.benibix.com/term/ai/depth-estimation
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
