Back to Courses
Advanced
Artificial Intelligence & Machine Learning
en
Machine Learning for Inverse Graphics
MIT OpenCourseWare
Platform
· Cambridge, USA
About this course
This graduate-level course covers fundamental and advanced techniques at the intersection of computer vision, computer graphics, and geometric deep learning. It lays the foundations of how cameras see the world, how to represent 3D scenes for artificial intelligence, how to learn to reconstruct these representations from only a single image, how to guarantee certain kinds of generalization, and how to train such models in a self-supervised way.
Prerequisite Skills
Skills you should have before taking this course
Deep Learning
linear algebra
probability and statistics
programming in Python
multivariable calculus
Skills Gained
Skills you will develop by completing this course
Machine Learning
Computer Vision
computer graphics
geometric deep learning
3D scene representation
inverse graphics
self-supervised learning
neural rendering
image-based 3D reconstruction