This course covers the fundamental theory and application of AI algorithms in the context of computer graphics. Deep learning is prevalent in graphics: from convolutional neural networks (CNNs) for denoising movie frames to Generative Adversarial Networks (GANs) for simulating facial animation. Through lectures, reading assignments (current research papers), and a semester long programming project, students will learn fundamental concepts including: supervised and unsupervised learning, convolutional neural network architectures, backpropagation, autoencoders and fine tuning, as well as applications like image denoising and GANs for video simulation and animation. Learn GPU programming on the new HiPerGator NVIDIA cluster.
Prior experience in computer graphics is not required. We will review background math and graphics concepts. This course is open to graduate and undergraduate students.