 |
MIT CSAIL6.869: Advances in Computer Vision |
 |
| Instructors | William T. Freeman | Antonio Torralba |
| Office: 32-D476 | Office: 32-D432 | |
| Office hours: Wednesday 2:30-3:30pm | Office hours: Monday 2:30-3:30pm | |
| TA | Michael Rubinstein | |
| Office hours: Tuesday 4-5pm (D4-south open area) | ||
| Course mailing list | 6.869-announce@mit.edu | |
| Staff email |  |
|
| Lecture | MW 1-2:30pm (66-168) | |
| Units | 3-0-9 (Graduate H-level, Area II AI TQE) | |
| Prerequisites | 6.041 or 6.042; 18.06 | |
Announcements
May 10, 2011: Presentation schedule
Remember to submit your presentations by 9am tomorrow!
Part I
Hoki Tam
Mark Richardson
Marzyeh Ghassemi and Xiaodan Jia
Mark Sullivan
Yichang Shih
Jennifer Chan
Patrick Barragan
Abe Davis
Hamed Alemohammad
Stav Braun
Joshua Slocum
Shih-Yu Sun
Andrew Sweet
Part II
Brent Tweddle (video)
Alison Laferriere
Ilia Lebedev
Cai GoGwilt
Stanislav Nikolov
Neal Wadhwa
Jacob Steinhardt
Nikhil Naik
Rui Li
Andrew Owens
Ami Patel
Jeff Bezanson
Cathy Wu
May 9, 2011: Problem set grades and course evaluation
The problem set grades are updated in Stellar. Also don't forget to fill out the course evaluation!
May 2, 2011:
Apr 20, 2011: Project report and presentation
Instructions for writing and submitting your final reports and presentations are available. Please read them carefully.
Apr 11, 2011: Pinhole image gallery
Is available here.
Mar 24, 2011: Project proposals
Final project proposals are due on April 4. See some related instructions here.
Mar 5, 2011: Problem Set 4 Hints
We have posted online a short document with some FAQ we got regarding problem set 4.
It is mostly intended for those who might still like to submit/resubmit to the OSA contest.
Don’t worry if you have already submitted your problem set. The issues that appear there will not have large influence on the grade.
Feb 28, 2011: Additional illuminant data for pset4
You can find the file train_data2.mat on the assignments page, which contains illuminant data from a different color database (the surface data is the same as before). You are welcome (but not required) to try your algorithm with this data to see whether it improves your results.
Feb 6, 2011: New classroom
Starting Monday Feb 7 we are moving to classroom 66-168.
Feb 4, 2011: pset1 problem 4
In the simpleworldY script, the comment in line 164 should be "dY/dt = 0" instead of "dY/dx = 0".
Feb 3, 2011: MATLAB Tutorial
We will have a MATLAB tutorial this Friday (tomorrow), Feb 4, 1-2pm at room 38-166.
Feb 2, 2011: Welcome to 6.869!
Make sure to check out the course info below, as well as the schedule for what's up ahead.
There will a MATLAB tutorial on Friday afternoon. The exact time and place will be announced.
Good luck with your semesters!
6.869 staff
Overview
This course covers fundamental and advanced topics in computer vision with a focus on image statistics, machine learning techniques, and applied vision for graphics. Topics include image representations, frequency analysis, texture models, shape-from-X algorithms, Bayesian inference, object and scene recognition, motion estimation and tracking, multi-view geometry, and image databases. Covers topics complementary to 6.801/6.866; these subjects may be taken in either order.
Assignments
The assignments in this class are comprised of problem sets and a final project. There are no exams or quizzes. Problem sets will be handed out on (almost) weekly basis. See the schedule for more details. Assignments will be posted online and are due in class by the end of the specified day's lecture. All assignments must be handed in. Grades will be given on a discrete 1-5 scale, where 1 is marginal performance and 5 is good performance.
The assignments are designed to give you both theoretical and practical experience with the material discussed in class. Since computer vision is an applied research field, parts of the assignments will involve programming and experimentation. Those are generally designed to be carried out in MATLAB, though we allow you to use any coding environment that is convenient for you. We care more about the report than the actual code.
You should submit a hard copy of your work in class, and upload your code (and all files needed to run it, images, etc) to stellar. Solutions will be posted on the class website one week after the assignment is due.
Late Policy. An up to one-week late submission is allowed once, no questions asked, and you can use it at your discretion (don't use it needlessly). Any additional unapproved late submission will be considered as unsubmitted work. Late submission is not allowed for the final project.
Collaboration Policy. We allow discussing problem sets with one or two classmates, but you must submit your own write-up and list your collaborators. You are allowed to collborate with one more student for the final project.
Final Project
The final project will allow you to explore in depth a topic covered in class which you found interesting and like to know more about. During the semester we will propose ideas for projects in the problem sets and lectures, and we also encourage the students to come up with their own ideas that entice them. The topic for the final project and its scope should be approved by the class staff.
Overall, the final project is comprised of (a) a project proposal, (b) a five-minute class presentation, and (c) a report documenting your work, results and conclusions. More details on each of these milestones will be given as its deadline approaches.
Grading
Grading will be based on our assessment of your understanding of the class material, and will be roughly comprised of:
- problem sets: 2/3
- final project: 1/3
Contribution to the class discussion will also be taken into account.
Text
A set of class notes which will be available on this website before each lecture. Additional recommended books and resources are listed in the course materials page. For those interested in further readings - the notes contain relevant references, and we will also post links to additional related papers before each class.
We have set up an nb group to facilitate discussion/questions regarding the class notes, and to allow you to easily report bugs and typos. If you have pre-registered to the class, you should have received an invitation to the discussion group. Let us know in case you haven't, or if you encounter any problem accessing it.
Last updated: 2/1/2011