SC 395 • Winter 2025

Image Generative Models in Computer Vision

By Viraj Shah (Research Scientist, Google) IIT Gandhinagar
Overview

Course Description

This short course provides a rigorous overview of the current state-of-the-art in generative modeling, transitioning from foundational adversarial techniques to modern diffusion and flow-based paradigms.

Designed for senior undergraduate and graduate students, the curriculum balances theoretical derivation (SDEs, ODEs, Flow Matching) with practical architectural implementation (Diffusion Transformers, LoRA, ControlNet). The course concludes with an exploration of frontier applications in engineering sciences and the ethical implications of synthetic media.

Prerequisites
  • Probability Theory (Probability Distributions, Conditional Probability, Gaussian Distribution, Divergence)
  • Linear Algebra (Matrix decompositions, Vector spaces)
  • Deep Learning Fundamentals (CNNs, Transformers, Backpropagation) & Python / PyTorch
📚 Refresher Materials
Curriculum & Schedule

Syllabus

Hands-On

Laboratory Sessions

Lab A: Foundations of GANs and Diffusion Models

Monday • 9:15 PM - 10:15 PM • Venue: AB 10/203
  • Implementing GAN from scratch
  • Implementing DDPM from scratch

Lab B: Flow Matching

Monday • 9:15 PM - 10:15 PM • Venue: AB 10/203
  • Flow Matching from Scratch
```