Machine Learning for Inverse Graphics

This course covers fundamental and advanced techniques in this field at the intersection of computer vision, computer graphics, and geometric deep learning. It will lay the foundations of how cameras see the world, how we can represent 3D scenes for artificial intelligence, how we can learn to reconstruct these representations from only a single image, how we can guarantee certain kinds of generalizations, and how we can train these models in a self-supervised way.

The syllabus, on MIT OpenCourseWare

The full course — syllabus, assigned readings, problem sets, exams, and lecture notes — lives on OCW. These open the real thing: