# 6.S058 Project https://introtocv.github.io/project.html | [![](https://introtocv.github.io/images/cv_logo1.jpg)](http://groups.csail.mit.edu/vision) | ### MIT CSAIL 6.S058: Introduction to Computer Vision | [![](https://introtocv.github.io/images/cv_logo2.jpg)](http://groups.csail.mit.edu/vision) | | --- | --- | --- | | ### Spring 2026 | | [[Home](https://introtocv.github.io/index.html) | [Policy](https://introtocv.github.io/policy.html) | [Schedule](https://introtocv.github.io/schedule.html) | [Course Materials](https://introtocv.github.io/materials.html) | [Final Project](https://introtocv.github.io/project.html) | [Piazza ](https://piazza.com/class/mkwwzxso70q31t/) | [Canvas](https://canvas.mit.edu/courses/37847) ] | ## Project Overview & Team Formation The final project is an opportunity for you to apply what you have learned in this class to a problem in computer vision that interests you. You can either pick one of the suggested project topics below (Option 1) or come up with your own project idea (Option 2). Your project must investigate a **scientific question**. It is not enough to do a literature review, nor to directly reimplement a method without making any changes to it. A good project is one where you have scoped out a reasonable problem and demonstrated first experimental evidence that your proposal is viable. We expect at least 30 hours of work per team member on the project, and we are allocating time in the schedule to accommodate this (the workload will be consistent with problem set expectations during the equivalent time period). We expect two-person projects to be about twice the amount of work and content as one-person projects. Although we recommend you work in teams, it is not required. **If you do decide to form a team** , please note that each team can have a **maximum of 2 members** and you and your project partner must be **registered in the same course**. Your project partner must be in **the same CI-M recitation section** as you. Further below you will find instructions regarding the project proposal, presentation, and report, and detailed grading rubrics. ## Project Topic ### Option 1: Choose one of the suggested project topics: * [ControlNet for Stable Diffusion](http://6.8300.csail.mit.edu/sp23/projects/ControlNet_for_Stable_Diffusion.pdf) * [Computer-Aided Diagnosis](http://6.8300.csail.mit.edu/sp23/projects/computer_aided_diagnosis.pdf) * [Stata Navigation](http://6.8300.csail.mit.edu/sp23/projects/stata.pdf) * [3D Printing Martian Rocks](http://6.8300.csail.mit.edu/sp23/projects/3DMartianRocks.pdf) * [3D Shape from 2D Surface Contours](http://6.8300.csail.mit.edu/sp23/projects/3d_from_contours.pdf) * [3D Shape Reconstruction](http://6.8300.csail.mit.edu/sp23/projects/3d.pdf) * [Imaging the Black Hole at the Center of the Milky Way](http://6.8300.csail.mit.edu/sp23/projects/VLBI.pdf) * [Scene Segmentation](http://6.8300.csail.mit.edu/sp23/projects/segmentation_proposal.pdf) * [NeRF: Neural Radiance Fields](http://6.8300.csail.mit.edu/sp23/projects/NeRF_Proposal.pdf) * [Motion Magnification for Planets](http://6.8300.csail.mit.edu/sp23/projects/wobbling_stars_project.pdf) * [Video Super Resolution](http://6.8300.csail.mit.edu/sp23/projects/video_superresolution.pdf) * [Visually Indicated Sounds](http://6.8300.csail.mit.edu/sp23/projects/vis.pdf) * [Drone and Satellite Image Alignment](https://introtocv.github.io/proposals/drone_satellite_image_alignment.pdf) * [Manga Panel Parser](https://introtocv.github.io/proposals/manga_parser.pdf) * [Object Tracking in Sports Footage](https://introtocv.github.io/proposals/object_tracking_sports.pdf) ### Option 2: Come up with your own project idea: You could select a topic in computer vision that interests you and create your own project around it. A potential project could focus on an application or on creating new models or improving existing ones: * Application: You could apply computer vision techniques to a specific application with your background and interest. * Models: You could create new models or improve previous models or methods, then evaluate them systematically on standard image datasets to demonstrate their strengths and weaknesses. ## Project Preparatory Assignment This is an **individual assignment** of **750–1,000 words** , due on March 13, 2026, and it will be assessed by the **communications instructor**. This preliminary assignment: * Asks you to familiarize yourself with the requirements of the Final Report. * Gives you an opportunity to start thinking about how you might approach the topics you’re most interested in. ## Article Review Assignment This is an **individual assignment** of **1,000 words** , due on April 3, 2026, and it will be assessed by the **communications instructor**. For this assignment, you will review an article related to your final project topic. In so doing, you will: * Analyze the writing and the technical approach of your chosen article * Discuss how the article informs and/or challenges your approach to your own project ## Draft of Final Project Introduction This assignment may be completed **individually or in pairs** , depending on whether you are collaborating on your Final Project Report. It is due on April 17, 2026 and will be assessed by the **communications instructor**. The purpose of this assignment is to give you an opportunity to receive feedback on the **introduction to your Final Project Report** , allowing you to revise and strengthen it before the final submission. ## Project Report Requirements This assignment may be completed **individually or in pairs** , depending on whether you are collaborating on your Final Project Report. **Two-person projects** are expected to involve approximately **twice the workload** of one-person projects, and students should expect to spend **at least 30 hours** on the project. The assignment is due on May 8, 2026 and will be assessed by **both the technical and communications instructors**. A rubric explaining what the communications instructors will look for in assessing the paper is linked in the Canvas assignment. The report should be **at least 5,000 words in length** for students working in partnerships, and **at least 3,500 words in length** for students working individually. The papers should not be too much longer than those required word counts. We will deduct points for excessively and unnecessarily long reports (a well-written concise report is better than a long and wordy one!). Furthermore, if you're part of a team, you should write the report together but you must include a section that **lists the individual contributions of each team member**. We will apply a penalty if this section is missing for 2-person teams. The report should be structured like a research paper, starting with an abstract, followed by sections for Introduction, Related Work, Methodology, Experimental Results, Discussion, Conclusion, and ending with references. Some of the sections can be combined if you want (specifically, Introduction/Motivation & Related Work as well as Results & Discussion). We require you write the report in the [CVPR format](https://cvpr2022.thecvf.com/sites/default/files/2021-10/cvpr2022-author_kit-v1_1-1.zip). 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. **Your introduction should incorporate revisions based on the feedback you received from your communications instructor on your draft.** accurate in describing the problem you tried to solve. Explain in detail your approach, and specify any simplifications or assumptions you have made. Also demonstrate the limitations of your approach. When doesn’t it work? Why? What steps would you have taken had you continued working on it? Make sure to add references to all related work you reviewed or used. **In the body of your paper, you should address the ethical considerations articulated in CVPR’s “Ethics Guidelines for Authors,” found[here](https://cvpr.thecvf.com/Conferences/2026/AuthorGuidelines).** **Submission:** The report is due **May 8 at 11:59 pm** and must be submitted in **PDF format**. Late submissions will not be accepted. If you're part of a team, only one of you should submit the PDF. In that case, please list both partners’ names and MIT Kerberos IDs (if you have one) at the top of the PDF and pay attention to the Canvas team submission details.