3D Reconstruction: Single Viewpoint
Discover the fundamental concepts of creating immersive 3D experiences, including VR/AR design, user experience, and programming.
Modules/Weeks
Weekly Effort
Discipline
School
Format
Cost
Course Description
- Explore the process of recovering 3D structure of a rigid scene from 2D images using a stationary camera.
- Estimate scene properties and address shape-from-shading challenges.
- Master techniques like surface normals estimation via photometric stereo and depth determination from defocus.
- Apply active illumination techniques for precise 3D reconstructions, understanding their significance in fields such as robotics, medical imaging, and film production.
Course Prerequisites
- Solid understanding of linear algebra and calculus fundamentals
- Familiarity with basic programming concepts in a procedural language for method implementation insights
- Programming skills are beneficial, though not mandatory
What You Will Learn
By the end of this course, learners will be able to:
Understand the principles of 3D reconstruction from 2D images, encompassing key radiometric concepts.
Apply techniques like photometric stereo, depth from defocus, and shape from shading for scene recovery.
Recognize the broad applications of active illumination in fields like robotics, medical imaging, and film special effects.
Implement algorithms and models associated with 3D reconstruction in practical scenarios.
Course Outline
Module 1: Introduction to first principles of computer vision
Module 2: Radiometry and reflectance
Module 3: Photometric stereo
Module 4: Shape from shading
Module 5: Depth from defocus
Module 6: Active illumination methods
Instructors
Shree K. Nayar is the T. C. Chang Professor of Computer Science at Columbia University. He heads the Columbia Vision Laboratory (CAVE), which develops advanced computer vision systems. His research is focused on three areas - the creation of novel cameras that provide new forms of visual information, the design of physics-based models for vision and graphics, and the development of algorithms for understanding scenes from images. His work is motivated by applications in the fields of digital imaging, computer vision, computer graphics, robotics, and human-computer interfaces.
Nayar received 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. For his research and teaching he has received several honors including the David Marr Prize (1990 and 1995), the David and Lucile Packard Fellowship (1992), the National Young Investigator Award (1993), the NTT Distinguished Scientific Achievement Award (1994), the Keck Foundation Award for Excellence in Teaching (1995), the Columbia Great Teacher Award (2006), the Carnegie Mellon Alumni Achievement Award (2009), the Helmholtz Prize (2019), and the IEEE PAMI Distinguished Researcher Award (2019). For his contributions to computer vision and computational imaging, he was elected to the National Academy of Engineering in 2008, the American Academy of Arts and Sciences in 2011, and the National Academy of Inventors in 2014.
Please note that there are no instructors or course assistants actively monitoring this course.