3D Reconstruction: Multiple Viewpoints
Explore the principles of 3D image recovery, including camera calibration, uncalibrated stereo, optical flow, and motion.
Modules/Weeks
Weekly Effort
Discipline
School
Format
Cost
Course Description
- Explore the intricate processes involved in recovering 3D structures from multi-camera captured images.
- Master the geometric model of cameras, including the identification of internal and external parameters.
- Dive into core computer vision techniques like binocular stereo, optical flow, and structure from motion, applicable in areas like robotics, virtual reality, and augmented reality.
- Understand the foundational concepts of computer vision, including the linear camera model and optical flow estimation using the Lucas-Kanade method, enabling effective 3D reconstruction in real-world applications.
Course Prerequisites
- Prior knowledge of linear algebra and calculus
- Programming skills are beneficial, though not mandatory
What You Will Learn
By the end of this course, learners will be able to:
Calibrate a camera by accurately estimating its internal and external parameters.
Perform both simple and uncalibrated stereo techniques for scene reconstruction.
Develop optical flow algorithms and design methods for determining scene structure and camera motion.
Apply computer vision techniques effectively in real-world scenarios, particularly in robotics and virtual/augmented reality environments.
Course Outline
Module 1: Introduction to first principles of computer vision
Module 2: Camera calibration
Module 3: Uncalibrated stereo
Module 4: Optical flow
Module 5: Structure from motion
Instructors
Shree K. Nayar is the T.C. Chang Professor of Computer Science at Columbia University and leads the Columbia Vision Laboratory. His research focuses on developing advanced computer vision systems for digital imaging, computer graphics, robotics, and human-computer interfaces. He has received numerous awards and honors for his research and teaching, including the David Marr Prize, the David and Lucile Packard Fellowship, and the National Young Investigator Award. Nayar has also been elected to the National Academy of Engineering, the American Academy of Arts and Sciences, and the National Academy of Inventors. He holds a BS degree in Electrical Engineering from Birla Institute of Technology, an MS degree in Electrical and Computer Engineering from North Carolina State University, and a PhD degree in Electrical and Computer Engineering from the Robotics Institute at Carnegie Mellon University.
Please note that there are no instructors or course assistants actively monitoring this course.