CS 763 Computer Vision (Even Sem, Jan 2022)

Quick Links:
Topics
Tasks
All Scores
Evaluation
Announcements
Resources
Midsemester Course Eval
Instructor: Sharat. Do NOT send email. Use piazza.
Office: Rekhi Bldg, A202
Office Hours: 30 min after class
Lecture hours: T/F 3:30 PM (Slot 11)
Lab: Fridays 2:15 to 5:15 (notional)
Venue: Virtual
Teaching Assistants: Not yet assigned
  • Recent Announcements (Last modified approximately at
    1. Welcome to the course. Note: Most links will not work.
    2. Please read "Course Pre-req" below and complete this this form ( before Jan 3 2pm deadline extended, see email.).
    3. Course description and material is changing somewhat from last time. To be updated.
    4. First Meeting Link. Password cs763
    5. Eventually we will move to Piazza, so regularly monitor piazza.. We have moved to Piazza. See lecture video posted there. Most dynamic content (e.g. discussions) appear there. The content in this page (usually lecture slides) is still valid. Therefore, you should periodically visit this page.
  • Informal Course Overview: In this course we build on what you have learnt (or learned:-) in an earlier digital imaging processing course. Given the above, in this course we will cover a proper subset of (in no particular order) [We will do "old CV" and "new CV" similar to last offerings ("deep learning") .] https://docs.google.com/forms/d/e/1FAIpQLScBHGJUwYgZNmUnIwGuo7kUObo6WLcwuS6bOCUItdN5hloL4w/viewform">
    • Multi-view geometry and Stereo vision
    • Structure from Motion
    • Shape from Shading
    • Features
    • Segmentation and region growing
    • Reading and presenting research papers.
    • Knowledge representation and inference
    • Object recognition and tracking
    • Texture classification and recognition
    • Activity recognition
    • Computational Photography and super-resolution
  • CS764 Lab : Because working hands-on is so-important in vision (for that matter in just about any CSE course barring, say, theory of computing), we have separate credits for a lab component. It's not the intention to jack up your load; this model is to ensure that you get (IMHO) proper credits for the work load compared to, say, a theory-only course. For this reason, the lab will follow the lectures. I have (tried to) set up the lab so that there are no conflicts.

    More about the lab when we meet.

  • Course Prerequisites (aka "who is allowed"):
    1. CS663 (Digital Image Processing) offered by CSE is a declared prerequisite (see below)
    2. In addition, students are expected to have basic programming skills (programming with loops, pointers, structures, recursion), linear algebra and matrix methods. (We will freshen up as required.)
    3. Audits are discouraged for all and prohibited for non-PhD candidates.
    4. The course is open (modulo the above) to any UG/PG in CSE (and folks who are going into IDDDP in CMinds)
    5. That said, the general goal is to "enable" all students who wish to be part of this course. Please note that we are talking about students, and not test-takers.
    6. Non-CSE (e.g. EE) will be considered. However, it's not kosher to repeat this course again (say after doing in EE) to jack up CPI.
    7. What if I want the course and not the lab? What if I want the lab and not the course? Discuss. (See point 5, 9).
    8. Exceptions will be made in cases based on written letters (i.e. email) (say, from people in the field, genuine reasons and so on). Discuss (see Point 9). Students should not send email (see point 5).
    9. For any exceptions, queries, genuine difficulties, discuss in the first week of classes at a designated time (to be established) but before drop-add deadline.
  • What I will discuss next
    1. Ransac. Format of the class.
    2. Ransac continued. Format of the class continued.
  • Notes on evaluation. This is important and at this time tentative .
    1. Grading
      • Class participation (Viva): Pass/Not Pass (5%-10%) (starts after course drop/add).
      • Regular Task X: 1--7 programming assignments: (approx x%)
      • Regular Task Y: 1--7 home work: (approx y% where x + y ~= (40-60))
      • Instructor Viva (not for everyone) to ensure you understand what you are doing. Viva can reduce marks for some people in group assignments.
      • Piazza Points: This will be used for generously tipping you when you are on the grade border.
    2. By default, I will asume that you will adhere to the following pledge (aka honour code)

      I pledge on my honour that I have not given or received any unauthorized assistance on this assignment or any previous task.

      and will write and sign this on EVERY submission that carries points. (You can use (Gita/Koran/Bible/Old Testament) (pick one) instead of "honour" in the above line. If you are not clear what unauthorized assistance means, please talk to me.

    3. Collaboration: By default, i.e., unless specified otherwise, you may discuss general ideas behind tasks with people in the course. What does this mean?
      • In any case, you are not to discuss this with external people -- anyone other than TA -- outside your course.
      • Needless to say, you are not allowed to take previous year's question papers or assignments. This will also apply in the future after you finish with this course when your juniors ask you.
      • Any electronic discussion must happen via Piazza. No WA.
      • By default, please feel free to take things from the Internet but do not plagiarize from the Internet, i.e., if you do end up having to use external sources you MUST cite these clearly
      • For SOME tasks, you may be expressly prohibited to look for solutions from the Internet. In such cases, finding answers to problems on the Web or from other outside sources (these include anyone not enrolled in the class) is strictly forbidden.
      • Some tasks will be in groups. You can discuss within this group, i.e., for these tasks, the group is the unit
      • In all cases, you cannot borrow something for which you claim points. More specifically, if you submit something, and out of the 100% you submitted, 80% is from the Internet, that is fine -- only if you give proper acknowledgment. You will be entitled to be graded out of 100% even if your work of 20% is purely yours. But if you do not include acknowledgment for the 80% but you acknowledging only 30%, then you are falsely claiming credit
        The same situation if you are discussing your task with people on, say, WA.

      Violation of this policy is considered serious and will be dealt with strictly. By reading these lines, you agree to these terms :-)

    4. Even if you miss the task deadline, you have to submit your assignment to prevent getting a fail grade. (There is no guarantee that you will get any credit for it.)
    5. If you miss a submission deadline or an exam, your marks will be rescaled (based on other assignments) ONLY in exceptional circumstances (medical reason for example). These must be approved by me BEFORE the due date in writing or via email. The default is that you get zero.
    6. The following is true for all electronic submissions. Late submission carry a leaky exponential penalty. Assignments submitted within the first 29 minutes after the deadline are considered 'on time'. However any assignment that is late by more than 29 minutes will attract the penalty (table is as follows, intervals are semi-closed, i.e. open on the right). Thus an assignment submitted 31 minutes late w.r.t. the original submission deadline will attract 5% penalty.
      Late submission in hours1-22-44-66-88-1010-1414-24late for more than 24 hours
      Penalty5%6%7%10%16%32%64%100% (You still have to submit it)
    7. Latedays:
      • Each student gets 3 latedays in total over the entire duration of the course. If a student chooses to use a lateday for a submission the late submission penalty will not apply (for that day only).
        This means, for example, if you turn in three assignments one day late, they could all be counted as on-time. Or, if you turn in a single assignment four days late, it could be considered only one day late.
      • Latedays are not divisible; as soon as a submission is 1 minute late, you must use a full lateday. If you are working on a task in a group, then every lateday you take will cost each partner one lateday.
      • When submitting an assignment, a student must state whether she is using free latedays, and if so, how many. This should be stated in the README file. If you do not state it, we will assume that you are going to use the lateday elsewhere and want to take the usual penalty scheme.
      • The usual penalty scheme will follow (as stated in the table) once the lateday is not applied on a day.
      • Unused latedays are not available for cashing, or for donation to a needy soul.
    8. Grade revision policy: Students have a habit for asking for more points on their exams. This is understandable. Please use the following policy for clarification of corrected papers:
      • If you have any questions on the grading, you must bring it to the attention of the professor concerned within 72 hours of receipt or the next lecture, whichever is earlier.
      • Please study the model answers before you question a decision. If you need to appeal a decision, please note that the instructor has the right to revise the marks of questions other than the ones you are debating.
      • I request that you do not ask frivolous questions. In particular, questions of the form "I think I should be given partial credit" are not welcome. You must instead use the objective criterion "Model answer states 2 marks for this step; I have written this step; please reevaluate".
  • Texts/References
    1. Text: Computer Vision by Ponce and Forsyth
    2. Other References in no particular order
      • Trucco & Verri. Introductory Techniques for 3-D Computer Vision
      • Rick Szeliski. Computer Vision: Algorithms & Applications
      • Hartley and Zissmeran. Multiple view geometry
  • Old Announcements
  • Solutions I used to post solutions, but nowadays I hand them out in class. Solutions may be occasionally posted and deleted asynchronously (in order that students from other courses do not suffer/benefit). 
  • Student Driven Course Evaluation.
    1. The anonymous midterm course evaluation process should happen week after midsem.