Course · Fall 2024 (archive)

Computer Vision

CS-GY 6643

A cat with bounding boxes labelling its head, ears, eyes, and nose

An important goal of signal processing and artificial intelligence (AI) is to equip computers with the capability of interpreting visual inputs. Computer vision is an area that deals with the construction of explicit, meaningful measurements and descriptions of physical objects from images. It includes many techniques from image processing, pattern recognition, geometric modeling, cognitive processing, and machine and deep learning. This course introduces students to the fundamental concepts and techniques in image processing and computer vision.

This is a graduate level course requiring working knowledge of linear algebra, data structures and proficiency in programming (python). Advanced undergraduates may enroll upon permission from instructor.

Course information

Instructor
Prof. Erdem Varol
Time
Thursdays 11am-1:30pm
Place
2 MetroTech Center, Room 801

Course team

Erdem Varol
InstructorErdem Varolev2240@nyu.edu
Rishabh Raj
TARishabh Rajrr4574@nyu.eduOffice hours: Tuesdays 1-2pm on Zoom
Malhar Patel
TAMalhar Patelmkp6112@nyu.eduOffice hours: Mondays 1-2pm on Zoom

Course details

Grading

Individual homework 18%, individual programming projects 45%, in-class midterm 15%, and final group project 22%.

Prerequisites

Working knowledge of linear algebra and data structures, plus proficiency in Python. Advanced undergraduates may enroll upon permission of the instructor.

Assignments and late policy

Homework and programming projects were submitted to Brightspace by 11:59pm on the due date. Programming projects were submitted as evaluated Jupyter notebooks.

Every hour that a project was late (rounded down) caused a 1% penalty on the total allotted grade.

Schedule

DateTopicMaterialsAssignments
September 5, 2024Intro and survey of topicsLecture 1 slides, Python tutorial, Google Colab SetupHomework 0 out: Join slack nyucomputervision.slack.com (Due September 11, 11:59pm)
September 12, 2024Image formation and filteringLecture 2 slides, Colab for Lecture 2, Szeliski 2.2, 2.3, 3.1, 3.2Homework 1 out, Project 1 out
September 19, 2024Non-linear filtering and edge detectionLecture 3 slides, Colab for Lecture 3, Szeliski 3.3, 7.2Homework 1 due, September 19 10:59a
September 26, 2024Image recognition, Feature detection and matchingLecture 4 slides, Colab for Lecture 4, Szeliski 6,7Final project team selection due, September 22 10:59am
October 3, 2024Contour tracking and Hough transformsLecture 5 slides, Colab for Lecture 5, Szeliski 7.3,7.4Project 1 due, October 4, 10:59am
October 10, 2024Image alignmentLecture 6 slides, Colab for Lecture 6, Szeliski 8.1,8.2Homework 2 out, Final project proposal due, October 11, 11:59pm
October 17, 2024SegmentationLecture 7 slides, Colab for Lecture 7, Szeliski 7.5Homework 2 due, October 18, 11:59pm
October 24, 2024Midterm exam (in class)Midterm Exam, Solution
October 31, 2024Machine learning, optimizationLecture 8 slides, Colab for Lecture 8Project 2 out (Due Nov. 18, 11:59am)
November 7, 2024Convolutional Neural NetsLecture 9 slides, Deep-STORM, 3D CNNsHomework 3 out, Nov. 8 (Due Nov 21,10:59am)
November 14, 2024Learning based recognitionLecture 10 slides, GradCAM, GradCAM ColabProject 2 due, November 18, 11:59am
November 21, 2024Motion models, depth estimation and optical flowLecture 11 slides, RAFT Paper PresentationHomework 3 due, November 21, 10:59am
November 28, 2024THANKSGIVING BREAK (No class)
December 5, 2024Learning based segmentationLecture 12 slidesProject 3 due, December 6, 11:59pm
December 12, 2024Final project presentationsPresentation InfoVideo submission due December 12, 08:00am Write-up and code due December 19, 11:59pm

This is the earliest archived version of this course.