Computer Vision

Computer Vision

About This Series

Computer vision is a field dedicated to extracting 3D information and scene understanding from images and videos. This series starts with the mathematical models of cameras and progresses through feature detection, stereo vision, Structure from Motion, and on to SLAM and NeRF.

Computer vision is widely used in autonomous driving, AR/VR, robotics, medical imaging, and many other fields.

Learning by Level

Introduction

Image and Camera Fundamentals

  • Digital Image Fundamentals
  • Pinhole Camera Model
  • Homogeneous Coordinates and Transformation Matrices
  • Camera Matrix

Basic

Features and Calibration

  • Feature Detection (Harris, SIFT, ORB)
  • Feature Matching
  • RANSAC
  • Camera Calibration

Intermediate

Stereo and 3D Reconstruction

  • Epipolar Geometry
  • Stereo Vision
  • Structure from Motion
  • Multi-View Stereo

Advanced

SLAM and Cutting-Edge Methods

  • Visual Odometry
  • SLAM
  • Deep Learning-Based Methods
  • NeRF / 3D Gaussian Splatting

Learning Path

Introduction Camera Basics Basic Features & Calib. Intermediate 3D Reconstruction Advanced SLAM & NeRF Intro: Images, camera models, coordinate transforms, projection Basic: Features, matching, RANSAC, calibration Intermediate: Epipolar geometry, stereo, SfM, MVS Advanced: VO, SLAM, deep learning, NeRF, 3DGS From 2D Images to the 3D World 2D Image Pixel Coordinates $(u, v)$ Feature Matching Multiple Views Epipolar Geometry Triangulation 3D Recovery 3D Model Point Cloud / Mesh $(X, Y, Z)$

Key Topics

Camera Geometry

Pinhole model, projective transformation, intrinsic and extrinsic parameters.

Feature Detection

Methods for detecting distinctive points in images, including Harris, SIFT, and ORB.

3D Reconstruction

Recovering 3D shapes through stereo vision, SfM, and MVS.

SLAM

Simultaneous localization and mapping: estimating position while building a map of the environment.

Related Fields