Optical Flow

Generative adversarial network (GAN)

Object Detection

Stereo

Neural network

Convolutional neural network (CNN)

Convolution

K-Nearest Neighbors

Linear Classifiers

Stochastic gradient descent (SGD)

Momentum

AdaGrad

Adam

Learning Rate Schedules

Support Vector Machine (SVM)

Softmax Loss

Multi-layer Perceptron

Backpropagation

Higher-level representations

Image Features

Pooling

Batch Normalization

Transfer learning

AlexNet, VGG, GoogLeNet, ResNet

Activation Functions

Data Processing

Weight initialization

Hyperparameter Tuning

Data Augmentation

Feature visualization and inversion

Adversarial Examples

DeepDream and Style Transfer

Single-stage detectors

Two-stage detectors

Semantic/Instance/Panoptic segmentation

Long Short-Term Memory (LSTM)

Gated recurrent unit (GRU)

Language Modeling

Image Captioning

Sequence-to-sequence (Seq2Seq)

Self-Attention

Transformer (machine learning model)

Video classification

3D CNNs

Two-stream networks

Multimodal Video Understanding

Supervised learning

Unsupervised learning

Pixel RNN, Pixel CNN

Variational autoencoder (VAE)

Pretext Tasks

Contrastive Learning

Multisensory Supervision

Stereo Vision

3D Shape Representations

Shape Reconstruction

Neural Implicit Representations

CS231n: Deep Learning for Computer Vision Stanford University Spring 2022 This is a deep-dive into the details of deep learning architectures for visual recognition tasks. The course provides students with the ability to implement, train their own neural networks and understand state-of-the-art computer vision research. It requires Python proficiency and familiarity with calculus, linear algebra, probability, and statistics. Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, localization and detection. Recent developments in neural network (aka “deep learning”) approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into the details of deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. During the 10-week course, students will learn to implement and train their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. Additionally, the final assignment will give them the opportunity to train and apply multi-million parameter networks on real-world vision problems of their choice. Through multiple hands-on assignments and the final course project, students will acquire the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks.  - Proficiency in Python  
    All class assignments will be in Python (and use numpy) (we provide a tutorial [here](http://cs231n.github.io/python-numpy-tutorial/) for those who aren't as familiar with Python). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Javascript) you will probably be fine.
- College Calculus, Linear Algebra (e.g. MATH 19 or 41, MATH 51)  
     You should be comfortable taking derivatives and understanding matrix vector operations and notation.
- Basic Probability and Statistics (e.g. CS 109 or other stats course)  
    You should know basics of probabilities, gaussian distributions, mean, standard deviation, etc. 

CS231n: Deep Learning for Computer Vision

Camera Models

Camera Calibration

Single View Metrology

Epipolar Geometry

Stereo Systems

Structure from Motion

Active Stereo

Volumetric Stereo

Fitting

Representation Learning

Monocular Depth Estimation

Feature Tracking

Scene Flow

Optimal Estimation

Neural Radiance Fields

CS 231A: Computer Vision, From 3D Reconstruction to Recognition Stanford University Winter 2023 This course introduces concepts and applications in computer vision, focusing on geometry and 3D understanding. It covers topics like filtering, edge detection, segmentation, clustering, shape reconstruction from stereo, and high-level visual topics. Knowledge of linear algebra, basic probability, and statistics is required. An introduction to concepts and applications in computer vision primarily dealing with geometry and 3D understanding. Topics include: cameras and projection models, low-level image processing methods such as filtering and edge detection; mid-level vision topics such as segmentation and clustering; shape reconstruction from stereo; high-level vision topics such as learned low-level visual representations; depth estimation and optical/scene flow; 6D pose estimation and object tracking. Prerequisites: linear algebra, basic probability and statistics.   

CS 231A: Computer Vision, From 3D Reconstruction to Recognition

Human Vision

Color Spaces

Transforms

Image Coordinates

Resizing

Filters

Edges and Features

Harris Corner Detector

Feature Matching

RANSAC (Random Sample Consensus)

HOG (Histogram of Oriented Gradients)

SIFT (Scale-invariant Feature Transform)

Depth Perception

Network Architectures

Semantic Segmentation

Instance Segmentation

Vision and Language

CSE 455 Computer Vision University of Washington Winter 2022 A general introduction to computer vision, this course covers traditional image processing techniques and newer, machine-learning based approaches. It discusses topics like filtering, edge detection, stereo, flow, and neural network architectures. This class is a general introduction to computer vision. It covers standard techniques in image processing like filtering, edge detection, stereo, flow, etc. (old-school vision), as well as newer, machine-learning based computer vision.   

CSE 455 Computer Vision

Image Filtering

Image Pyramids

Frequency Domain

Hough Transform

Detecting Corners

Feature Detectors and Descriptors

2D Transformations

Image Homographies

Geometric Camera Models

Two-View Geometry

Image Classification

Alignment and Tracking

Radiometry and Reflectance

Photometric Stereo

Digital Photography

16-385 Computer Vision Carnegie Mellon University Spring 2022 This course gives an expansive introduction to computer vision, focusing on image processing, recognition, geometry-based and physics-based vision, and video analysis. Students will gain practical experience solving real-life vision problems. It requires a good understanding of linear algebra, calculus, and programming. This course provides a comprehensive introduction to computer vision. Major topics include image processing, detection and recognition, geometry-based and physics-based vision and video analysis. Students will learn basic concepts of computer vision as well as hands on experience to solve real-life vision problems.  This course requires familiarity with linear algebra, calculus, basic probability, as well as programming. In particular, the following courses serve as prerequisite:

- "Mathematical Foundations of Electrical Engineering" (18-202) and "Principles of Imperative Computation" (15-122)

OR

- "Matrix Algebra with Applications" (21-240) and "Matrices and Linear Transformations" (21-241) and "Calculus in Three Dimensions" (21-259) and "Principles of Imperative Computation" (15-122) Readings will be assigned from the following textbook (available online for free):

- **Computer Vision**: Algorithms and Applications, by Richard Szeliski.
Additional readings will be assigned from relevant papers. Readings will be posted on the website.

The following textbooks can also be useful references for different parts of the class, but are not required:

- Multiple View Geometry in Computer Vision, by Richard Hartley and Andrew Zisserman.
- Computer Vision: A Modern Approach, by David Forsyth and Jean Ponce.
- Digital Image Processing, by Rafael Gonzalez and Richard Woods.

16-385 Computer Vision

Computer Vision (CV) is a field of developing algorithms and systems that make computers understand visual data from the world. Its applications include image and video recognition, object detection, visual tracking and surveilance, etc. It uses techniques from other fields of Computer Science such as [*Maching Learning*](/topic/machine-learning) and [*Deep Learning*](/topic/deep-learning).

Computer Vision

Computer Science

Computer Vision

Prerequisites

Common concepts