Project proposal due: Mon May 6, 2019 by 1:30pm (before class)
Final presentations due: Wed June 5 by 1:30pm (before class)
Final code and paper due: Fri June 7 by 11:59pm
The purpose of the final project is to provide hands-on experience designing, implementing, and evaluating a new computational video manipulation technique, algorithm or tool. Projects will be carried out by a team of up to 2 people. Your project should address a concrete video manipulation problem and should propose a novel, creative solution. The final deliverable will be an implementation of the proposed solution and a paper written in the format of a conference paper submission. In addition, each group will be responsible for giving a short presentation about the project on the final day of the class (Wed June 5).
Suggested Project Topics
To get you started in thinking about project ideas we have a number of final project suggestions for you to consider.
Project Proposal (due Mon 5/6 before class)
As a first step you should create a project proposal that includes the names of the members of your group and a short (1 to 2 paragraph) description of the project and the approach you plan to use. You should submit the proposal via Canvas.
Final Project Presentation (due Wed 6/5 in class)
We will hold a presentation of the final projects on Wed June 5, from 1:30pm to 3pm in class. The presentation will give you a chance to show off the hard work you put into your project, and to learn about the projects of your peers. Be prepared to give a 5-10 minute oral slide presentation. You should include a demo of your project.
You should upload your final project presentation slides with your final project code and paper on Monday 6/10 using the link given below.
Final Project Deliverables - Code and Paper (due Mon 6/10 by 11:59pm)
The final deliverables will include:
Code: an implementation of your project (source code and executable).
Paper: an 6-8 page paper written in the form of a conference paper submission. The paper should present related work, a detailed description of your system and a discussion of your design.
Submission: You should submit your final deliverables (access to a running executable and a zip file of the code, or a link to a github repository as well as a pdf of the paper and the slides you used for the in-class presentation) via Canvas.
The final paper should be in the style of a conference paper submission. The paper should include content that is typical of papers that appear at SIGGRAPH, or CVPR. In particular it should contain:
Introduction - An explanation of the problem and the motivation for solving it.
Related Work - A description of previous papers related to your project.
Methods - A detailed explanation of the techniques and algorithms you used to solve the problem.
Results - Screenshots of the videos your system produces and data to help evaluate your approach. For example you may include running times, or the time users typically spend generating a video using your system.
Discussion - What has the audience learned from your work?
Future Work - A description of how your system could be extended.
Your final paper should be formatted using the formatting of papers that appear at SIGGRAPH or CVPR. Although there are some differences in format between these conferences, you are free to pick from any of these two. If you need help finding a formatting template talk to us.