Course · Fall 2025 (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 explores the core concepts and practical techniques of image processing and computer vision at an intermediate level of depth and application.

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
Room 202, 370 Jay St

Course team

Erdem Varol
InstructorErdem Varolev2240@nyu.edu
Visweswar Sirish Parupudi
TAVisweswar Sirish Parupudivsp7230@nyu.eduOffice hours: Thursday 1-5pm in-person, 4-5pm on Zoom
Subhrajit Dey
TASubhrajit Deysd5963@nyu.eduOffice hours: Wednesday 1-2pm on Zoom
Nalini Ramanathan
TANalini Ramanathannar8991@nyu.eduOffice hours: Mondays 2-3pm on Zoom

Course details

Grading

Individual homework 15%, in-class midterm 25%, and programming projects 60%. Twenty percent of the programming project grade was competition based.

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 4, 2025Intro and survey of topics, Image Formation and FilteringLecture 1 slides, Python tutorial, Google Colab Setup, Code LabHomework 0 out on Brightspace: Join slack nyucomputervision.slack.com (Due September 11, 11:59pm)
September 11, 2025Non-linear filtering and edge detectionLecture 2 Slides, Code Lab, Szeliski 2.2, 2.3, 3.1, 3.2Homework 1 out; Project 1 out; Kaggle Invitation Link: Join Here
September 18, 2025Image recognition, Feature detection and matchingLecture 3 Slides, Code LabHomework 1 due - Solutions
September 25, 2025Contour tracking and Hough transformsLecture 4 Slides, Code Lab, Szeliski 6, 7Project 1 due
October 2, 2025Image alignmentLecture 5 Slides, Code LabHomework 2 out
October 9, 2025SegmentationLecture 6 Slides, Code LabHomework 2 due
October 16, 2025Midterm exam (in class)Project 2 out
October 23, 2025Machine Learning ,Backprop with MLP, Neural NetworksLecture 7 Slides, Code Lab
October 30, 2025Convolutional Neural Networks; YOLOLecture 8 slides, Colab for Lecture 8Homework 3 out ; Project 2 due
November 6, 2025Motion models, depth estimation and optical flowLecture 9 slides, Colab for Lecture 9Homework 3 due; Project 3 out
November 13, 2025Self Supervised Learning, CLIP EmbeddingsLecture 10 Slides, Code Lab
November 20, 2025Attention Mechanism, Vision TransformerLecture 11 Slides, Code LabProject 3 due; Project 4 out
November 27, 2025THANKSGIVING BREAK (No class)
December 4, 2025Vision Language ModelsLecture 12 Slides, Code Lab
December 11, 2025Additional TopicsWrap Up Slides
December 18, 2025No ClassProject 4 due

The previous version of this course is available here: Fall 2024.