- Instructor: Arjun Jain
- Office: 216, CSE New Building
- Email: ajain@cse DOT iitb DOT ac DOT in
- Teaching Assistants: Rishabh Dabral, Safeer Afaque
- Class Room: SIC201
- Instructor Office Hours (in room 216 CSE New Building): TBD
- [8/01/19] Monday class to be moved to 7pm slot to accommodate 3rd year students
- [14/01/19] The classroom has been moved to SIC201 (slots 13A and 15A) due to overflow in CC105
- [17/01/19] Assignment 1 has been released and is due by 27th Jan.
- [30/01/19] Assignment 2 has been released and is due by 8th Feb.
- [10/02/19] Assignment 3 has been released and is due by 20th Feb.
- [13/03/19] Assignment 4 has been released and is due by 23rd March.
- [10/04/19] Assignment 5 has been released and is due by 21st April.
- [10/04/19] End-term project evaluation will be held on 6th May.
- Deep Learning in computer vision: the data-driven paradigm, feed forwards networks, back-propagation and chain rule; CNNs and their building blocks, generative adverserial networks (GANs), Variational Autoencoders (VAEs) and Conditional Variational Autoencoders (CVAEs)
- Deep Learning applications including face detection, CNN compression, siamese and triplet networks and applications to face recognition
- Camera geometry, camera calibration, vanishing points, important transformations, homographies
- Image registration: RANSAC for point-matching, SIFT overview
- Algorithms for: shape from shading, optical flow, Kanade-Lucas-Tomasi algorithm, applications of optical flow
- Photometric stereo - deriving shape from multiple images of an object taken under different lighting conditions; applications to illumination invariant face recognition, face relighting
- Stereo (geometric binocular): epipolar geometry and fundamental matrix, the correspondence problem and shape from stereo; structure from motion
- Lecture slides that will be regularly posted
- Computer Vision: Algorithms and Applications, by Richard Szeliski
- Fundamentals of Computer Vision, by Mubarak Shah
- Deep Learning, by Ian Goodfellow and Yoshua Bengio and Aaron Courville
- All iTorch notebooks for topics covered in class can be found here
- Mid-sem exam: 20%
- Final exam (cumulative): 20%
- Assignments (five or six): 35% (all to be done in groups of 2-3 students)
- Course project: 20% (to be done in the same group of 2-3 students)
- Class participation: 5%
- Course project work will be presented by the student group during a viva at the end of the course. During this viva, each student in the group will be separately questioned, not only on the project work, but also the assignments. Each student is expected to contribute to each and every assignment and the course project.
- Audit requirements: You must write both exams, submit all assignments and the project, and score at least 40% to get an AU.
- Assignments will be given out (typically) once every two or three weeks. They must be submitted on or before the deadline. No late assignments will be accepted. The programming components of the assignments will typically involve MATLAB and lua, so you must be willing to learn it quickly.
- We will adopt a zero-tolerance policy against any forms of plagiarism or any other form of cheating. Just don't do it! In cases of plagiarism, givers and takers will both be considered equally responsible.
- This course is (inherently) cumulative. The syllabus for the final exam will include everything taught during the semester.
- Assignment 1 on Camera Geometry has been released and is due by 27th Jan.
- Assignment 2 on Camera Calibration, Image Alignment and Robust Methods has been released and is due by 8th Feb.
- Assignment 3 on Neural Network and Backpropagation has been released and is due by 20th Feb. Please use this Kaggle link to test your predictions and class standing.
- Assignment 4 on Recurrent Neural Network has been released and is due by 23rd March. Please use this Kaggle link to test your predictions and class standing.
- Assignment 5 on Lucas-Kande Tracker and Video Stabilization has been released and is due by 21st April.
| Date | Topics | Slides | iTorch Notebooks | Extra Reading |
|---|---|---|---|---|
| 7th Jan, 2019 |
|
Slides | -- | -- |
| 8th Jan, 2019 |
Camera Geometry
|
Slides | -- | Homogeneous Representations of Points, Lines and Planes |
| 14th Jan, 2019 |
|
Slides | -- | -- |
| 15th Jan, 2019 |
|
Slides | -- | -- |
| 21st Jan, 2019 |
|
Slides | -- |
Resource on SVD Additional slides and notes on solving homogenous least squares problem |
| 22nd Jan, 2019 |
|
Slides | -- | -- |
| 28th Jan, 2019 |
|
Slides | -- | -- |
| 29th Jan, 2019 |
Robust Methods in Computer Vision
|
Slides | -- | -- |
| 4th Feb, 2019 |
Deep Learning for Computer Vision
|
Slides | KNN | Matrix calculus reminder |
| 5th Feb, 2019 |
|
Slides | Gradient Check, Linear Layer | ADAM,
Nesterov DL optimization algorithms overview |
| 11th Feb, 2019 |
|
Slides | Convolution | Convolution arithmetic for deep learning |
| 12th Feb, 2019 |
|
Slides | Transposed convolution, MaxPool, Cross Entropy | -- |
| 18th Feb, 2019 |
|
Slides | Weight Initialization | -- |
| 19th Feb, 2019 |
|
Slides | -- | -- |
| 4th March, 2019 |
|
Slides | -- | -- |
| 5th March, 2019 |
|
Slides | -- | -- |
| 11th March, 2019 |
|
Slides | -- | -- |
| 12th March, 2019 |
|
Slides | -- | -- |
| 18th March, 2019 |
|
Slides 1 Slides 2 | -- | -- |
| 26th March, 2019 |
Orthographic Structure from Motion
|
Slides | -- | -- |
| 1st April, 2019 |
Optical Flow
|
Slides | -- | -- |
| 2nd April, 2019 |
|
Slides | -- | -- |
| 8th April, 2019 |
Kanade-Lucas-Tomasi (KLT) Featurepoint Tracker
|
Slides | -- | Lucas-Kanade 20 Years On: A Unifying Framework |
| 9th April, 2019 |
Geometric Stereo
|
Slides | -- | -- |
| 15th April, 2019 |
|
Slides | -- | Epipolar Geometry |
| 16th April, 2019 |
|
Slides | -- | -- |