DS265-Deep Learning For Computer Vision

Instructors: R. Venkatesh Babu

Teaching Assistant: Badrinath Singhal, Priyam Dey and Varun Varma Thozhiyoor

Classroom timings & venue: Tue/Thu 4PM - 5:30PM at CDS 102

Tutorial timings & venue: Fri 11:30AM - 1:00PM at CDS 102

Note: Tutorials will generally be held depending on the course requirements or requests from the students.

Course Registration Form: Link to Google Form Filling up the Google form is compulsory.

Teams Code (2026 DLCV): t21qooo

In the recent years, Deep Learning has pushed to boundaries of research in many fields. This course focuses on the application of Deep Learning in the field of Computer Vision. The first half of the course formulates the basics of Deep Learning, which are built on top of various concepts from Image Processing and Machine Learning. The second half highlights the various flavors of Deep Learning in Computer Vision, including Generative Models (VAE, GANs, Diffusion Models, Flow Matching), 3D reconstruction (NeRFs, 3D Gaussian Splatting etc), Recurrent Models, and Deep Reinforcement Learning Models, as well as foundational models such as Stable Diffusion.

Prerequisites

Primary (crucial): Machine Learning and Computer Vision / Image Processing

Secondary (familiarity preferred): Probability, Statistics and Linear Algebra.

1. Thoroughly Understanding the fundamentals of deep learning.
2. Gaining knowledge of the different modalities of deep learning currently used.
3. Gaining Knowlegde about state-of the art models and other important works in recent years.
4. Learning the skills to implement deep learning based AI systems (use of multiple packages etc.)