MIT CSAIL 6.S058: Introduction to Computer Vision
Spring 2026
[Home | Policy | Schedule | Course Materials | Final Project | Piazza | Canvas ]

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
• Computer-Aided Diagnosis
• Stata Navigation
• 3D Printing Martian Rocks
• 3D Shape from 2D Surface Contours
• 3D Shape Reconstruction
• Reconstructing 3D Structure from Drawing & Sketches
• Imaging the Black Hole at the Center of the Milky Way
• Scene Segmentation
• NeRF: Neural Radiance Fields
• An Automatic Metric for Surprisal
• Motion Magnification for Planets
• Video Super Resolution
• Visually Indicated Sounds

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.

The report should at least 5,000 words in length, and not too much longer. 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.

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 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.

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 Gradescope team submission details.