Deep Vision and Graphics

Lectures on deep learning for computer vision and graphics, covering ConvNets, transformers, detection, segmentation, generative models, and neural rendering.

Instructor: Michael Diskin

Term: Fall

Overview

Lecturer in the Deep Vision and Graphics course at YSDA (co-developed with Skoltech). Topics span ConvNet architectures, vision transformers, object detection, semantic segmentation, generative models (VAE, GAN, diffusion), and neural rendering (NeRF).

Course repository on GitHub