16-720 Computer Vision

Carnegie Mellon University · Fall 2026

Syllabus Thumbnail of the 16-720 syllabus

Time / Location: Tue / Thu, 3:30–4:50 PM · TEP 1403

Kris KitaniInstructor
Ce ZhangTA
Wenli XiaoTA
Vihaan MisraTA
Aviral ChhariaTA
Manan ShahTA

This course covers core ideas in computer vision, including image formation, filtering, recognition, geometry, 3D vision, and modern vision and generative models, with an emphasis on fundamental principles and influential recent work.

Enrolled students should use Canvas for course materials, assignments, announcements, and class resources.

Schedule

DateNo.Topic
Aug 25L1Introductions, Policies, Grading, Applications of Computer Vision
Aug 27L2Filtering and Image Pyramids
Sep 1L3Fourier Domain
Sep 3L4Image Boundaries and Gradient Filters
Sep 8L5Feature Detection
Sep 10L6Feature Descriptors
Sep 15L7Image Representations: GIST, Bag of Visual Words
Sep 17–Checkpoint 1 (35 minutes), lecture continuation
Sep 22L8Classification Methods: K-NN, Naive Bayes, SVM
Sep 24L9Neural Networks: Perceptron, Gradient Descent, SGD
Sep 29L10Initialization, Learning Rates, and Optimization Algorithms
Oct 1L11CNNs and Image Classification
Oct 6L12Object Detection
Oct 8L13Vision Transformers
Oct 13–NO CLASS — Fall Break
Oct 15–NO CLASS — Fall Break
Oct 20L142D Transformations: Euclidean, Similarity, Affine, Projective
Oct 22–Checkpoint 2 (60 minutes), lecture continuation
Oct 27L15Homography Estimation
Oct 29L16Single-View Geometry
Nov 3–NO CLASS — Democracy Day
Nov 5LXXSpecial Topics / Buffer / Guest Lecture
Nov 10L17Camera Models, Pose Estimation, and Triangulation
Nov 12L18Epipolar Geometry
Nov 17L19Structure from Motion
Nov 19–Checkpoint 3 (35 minutes), lecture continuation
Nov 24L20Stereo, Optical Flow, and Image Alignment
Nov 26–NO CLASS — Thanksgiving
Dec 1LXXGenerative Models (e.g., GANs, Diffusion)
Dec 3LXX3D Representations (e.g., NeRF, Gaussian Splatting)