MIT CSAIL

6.869: Advances in Computer Vision

Fall 2012

[ Home | Schedule | Course Materials | Assignments ]

 

Problem Sets

Please submit a hard copy of your work in class, and upload your code (and all files needed to run it, images, etc) to stellar.

  Posted Due  
Problem set 1: A Simple Visual System Sep 6, 2012 Sep 20, 2012 pset1.pdf
code.zip
Problem set 2: Filtering Statistical models of images Sep 24, 2012 Oct 9, 2012 pset2.pdf
code.zip
Problem set 3: Anaglyph Camera Obscura Oct 4, 2012 Oct 23, 2012 pset3.pdf

 

Final Project

Project Proposal
Due: Nov 06 2012 11:59PM;

The proposals should be just a page, and should describe what you plan to do (and who with, if appropriate).  In the proposal, persuade us that it will be feasible for you to do it: lay out the tasks, and give a timeline for when you'll do each task. You can work by yourself or in pairs. Projects by pairs should be correspondingly more substantial.

Regarding the project topics: It should be something you're excited about. Anything related to computer vision is fine. We can help you with topics if you want ideas.  We want it to be something new that you do for this class, so you can't submit a paper you've done for your RA or a project from another class.  But something topically related to your RA is fine, and if it becomes a paper you submit for publication, that's ideal, of course.

Presentation
Due: TBD;

The project presentation should be clear, informative, and short. You should briefly describe the problem you have chosen, and present an overview of your approach and results. The time allotted to each presentation is 5 minutes. We’ll have to be strict with the timing to accommodate all the students, so make sure your presentation fit within that time.

Submission: We will use one computer for the presentations in order to avoid the cost of everyone setting up their laptops. You should upload your presentation to stellar by the due time above as a single ppt or pdf file named <YOUR_LAST_NAME>.ppt (or .pdf). If your presentation has additional files (e.g. videos), upload it as a single zip file with the same naming convention. Late submissions are not allowed, and no further editing will be possible after submission.

Report
Due: TBD;

The report should be 5 - 8 pages (the upper limit of 8 pages is strict!) in CVPR format. It should be structured like a research paper, with sections for Introduction, related work, the approach/algorithm, experimental results, conclusions and references.
You should describe and evaluate what you did in your project, which may not necessarily be what you hoped to do originally. A small result described and evaluated well will earn more credit than an ambitious result where no aspect was done well. Be accurate in describing the problem you tried to solve. Explain in detail your approach, and specify any simplifications or assumptions you have taken. Also demonstrate the limitations of your approach. When doesn’t it work? Why? What steps would you have taken have you continued working on it? Make sure to add references to all related work you reviewed or used.

You are allowed to submit any supplementary material that you think it important to evaluate your work, however we do not guarantee that we will review all of that material, and you should not assume that. The report should be self-contained.

Submission: submit your report to stellar as a pdf file named <YOUR_LAST_NAME>.pdf. Submit any supplementary material as a single zip file named <YOUR_LAST_NAME>.zip. Add a README file describing the supplemental content. Late submissions are not allowed.