Monthly Subscription Starting at AED 99 + VAT

3D Reconstruction - Multiple Viewpoints
  • Level Foundation
  • Duration 9 hours
  • Course by Columbia University
  • Offered by

About

This course focuses on the recovery of the 3D structure of a scene from images taken from different viewpoints. We start by first building a comprehensive geometric model of a camera and then develop a method for finding (calibrating) the internal and external parameters of the camera model. Then, we show how two such calibrated cameras, whose relative positions and orientations are known, can be used to recover the 3D structure of the scene. This is what we refer to as simple binocular stereo. Next, we tackle the problem of uncalibrated stereo where the relative positions and orientations of the two cameras are unknown. Interestingly, just from the two images taken by the cameras, we can both determine the relative positions and orientations of the cameras and then use this information to estimate the 3D structure of the scene. Next, we focus on the problem of dynamic scenes. Given two images of a scene that includes moving objects, we show how the motion of each point in the image can be computed. This apparent motion of points in the image is called optical flow. Optical flow estimation allows us to track scene points over a video sequence. Next, we consider the video of a scene shot using a moving camera, where the motion of the camera is unknown. We present structure from motion that takes as input tracked features in such a video and determines not only the 3D structure of the scene but also how the camera moves with respect to the scene. The methods we develop in the course are widely used in object modeling, 3D site modeling, robotics, autonomous navigation, virtual reality and augmented reality.

Modules

Welcome to First Principles of Computer Vision: 3D Reconstruction - Multiple Viewpoints

    • 6 Readings
Show info about module content

6 Readings

  • Course Syllabus
  • About the Instructor
  • Course Information and Support
  • Academic Honesty Policy
  • Discussion Forum Etiquette
  • Frequently Asked Questions

Pre-Course Survey

    • 1 Readings
    • 1 Plugin
Show info about module content

1 Readings

  • Pre-Course Survey

Week 1: Introduction to First Principles of Computer Vision

    • 2 Discussion
    • 7 Plugin
Show info about module content

2 Discussions

  • Introductions
  • Week 1 Questions and Feedback

Week 2: Camera Calibration

    • 1 Readings
    • 2 Discussion
    • 5 Plugin
    • 5 Assignment
Show info about module content

5 Assignment

  • 2.1 Overview of Camera Calibration Self-Check Quiz
  • 2.2 Linear Camera Model Self-Check Quiz
  • 2.3 Camera Calibration Self-Check Quiz
  • 2.4 Intrinsic and Extrinsic Matrices Self-Check Quiz
  • 2.5 Simple Stereo Self-Check Quiz

2 Discussions

  • Week 2 Camera Calibration
  • Week 2 Questions and Feedback

1 Readings

  • 2.2 Video Correction

Week 2 Quiz

    • 1 Assignment
Show info about module content

1 Assignment

  • Week 2 Camera Calibration

Week 3: Uncalibrated Stereo

    • 2 Readings
    • 2 Discussion
    • 7 Plugin
    • 6 Assignment
Show info about module content

6 Assignment

  • 3.2 Problem of Uncalibrated Stereo Self-Check Quiz
  • 3.3 Epipolar Geometry Self-Check Quiz
  • 3.4 Stereo Vision in Nature Self-Check Quiz
  • 3.5 Estimating Fundamental Matrix Self-Check Quiz
  • 3.6 Finding Correspondences Self-Check Quiz
  • 3.7 Computing Depth Self-Check Quiz

2 Discussions

  • Week 3 Simple Binocular Stereo System
  • Week 3 Questions and Feedback

2 Readings

  • 3.5 Video Correction
  • 3.7 Video Correction

Week 3 Quiz

    • 1 Assignment
Show info about module content

1 Assignment

  • Week 3 Uncalibrated Stereo

Week 4: Optical Flow

    • 1 Readings
    • 1 Discussion
    • 6 Plugin
    • 5 Assignment
Show info about module content

5 Assignment

  • 4.2 Motion Field and Optical Flow Self-Check Quiz
  • 4.3 Optical Flow Constraint Equation Self-Check Quiz
  • 4.4 Lucas-Kanade Method Self-Check Quiz
  • 4.5 Coarse-to-Fine Flow Estimation Self-Check Quiz
  • 4.6 Application of Optical Flow Self-Check Quiz

1 Discussions

  • Week 4 Questions and Feedback

1 Readings

  • 4.4 Video Correction

Week 4 Quiz

    • 1 Assignment
Show info about module content

1 Assignment

  • Week 4 Optical Flow

Week 5: Structure from Motion

    • 2 Readings
    • 2 Discussion
    • 5 Plugin
    • 5 Assignment
Show info about module content

5 Assignment

  • 5.1 Overview of Structure From Motion Self-Check Quiz
  • 5.2 Structure from Motion Problem Self-Check Quiz
  • 5.3 Observation Matrix Self-Check Quiz
  • 5.4 Rank of Observation Matrix Self-Check Quiz
  • 5.5 Tomasi-Kanade Factorization Self-Check Quiz

2 Discussions

  • Week 5 Structure from Motion
  • Week 5 Questions and Feedback

2 Readings

  • 5.3 Video Correction
  • 5.4 Video Correction

Week 5 Quiz

    • 1 Assignment
Show info about module content

1 Assignment

  • Week 5 Structure from Motion

Post-Course Survey

    • 1 Readings
    • 1 Plugin
Show info about module content

1 Readings

  • Post-Course Survey

Auto Summary

Explore the fascinating world of 3D Reconstruction from Multiple Viewpoints in this foundational Data Science & AI course by Coursera. Guided by expert instructors, you'll delve into camera geometry, calibration, binocular and uncalibrated stereo, optical flow, and structure from motion. Perfect for beginners, this 540-minute course is essential for careers in robotics, autonomous navigation, and virtual reality. Available through a Starter subscription.

Shree Nayar
Instructor

Shree Nayar