Phase 5: CV Deployment & Applications · ~60 minutes · Python

Monocular Depth & Geometry Estimation

A depth map is a single-channel image where each pixel is a distance from the camera. Predicting it from one RGB frame used to be impossible without stereo or LiDAR. In 2026 a frozen ViT encoder plus a lightweight head gets within a few percent of ground truth.

What you will learn

Distinguish relative and metric depth and state which one each production model (MiDaS, Marigold, Depth Anything V3, ZoeDepth) solves
Use Depth Anything V3 (DINOv2 backbone) to predict depth for arbitrary single images with no calibration
Explain why monocular depth works at all from a single image (perspective cues, texture gradients, learned priors) and what it cannot recover (absolute scale, occluded geometry)
Lift 2D detections to 3D points using a depth map and pinhole camera intrinsics

Introduction

Type: Build + Use
Languages: Python
Prerequisites: Vision Transformers (ViT), Self-Supervised Vision — SimCLR, DINO, MAE, Semantic Segmentation — U-Net
Time: ~60 minutes

Objective

Learning objectives

Distinguish relative and metric depth and state which one each production model (MiDaS, Marigold, Depth Anything V3, ZoeDepth) solves
Use Depth Anything V3 (DINOv2 backbone) to predict depth for arbitrary single images with no calibration
Explain why monocular depth works at all from a single image (perspective cues, texture gradients, learned priors) and what it cannot recover (absolute scale, occluded geometry)
Lift 2D detections to 3D points using a depth map and pinhole camera intrinsics

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card.