Course - Computer Vision MT25

Created: October 09, 2025 | Updated: May 18, 2026 | Read markdown | About these notes | View in context | Study these flashcards

---

• Course webpage (old)
• Lecture notes (from previous year)
  • 1, Introduction
  • 2, Image enhancement
  • 3, 2D Fourier transforms and applications
  • 4, Image restoration
  • 5, Matching, indexing, and search
  • 6, Image classification
  • 7, Convolutional networks
  • 8, Transformer networks for images
  • 9, Visualisation and understanding
  • 10, Object detection
  • 11, Image segmentation
  • 12, Videos
  • 13, Tracking
  • 14, Camera models and triangulation
  • 15, Multiple view geometry
  • 16, Generative models
  • 17, Representation learning
  • 18, Unsupervised computer vision
  • 19, Vision and language
  • 20, Ethics and privacy
• My notes here are based primarily on the slides above, written by Prof. Christian Rupprecht.
• Lecture recordings
  • 2024-2025
  • 2025-2026
• Practicals
• Other courses this term: Courses MT25^U

Notes

• Notes - Computer Vision MT25, Overview of results and methods^U

• Notes - Computer Vision MT25, Image representation^U
• Notes - Computer Vision MT25, Sampling and reconstruction^U
• Notes - Computer Vision MT25, Subsampling and upsampling^U
• Notes - Computer Vision MT25, Image transformations^U
• Notes - Computer Vision MT25, Homogenous coordinates and homographies^U
• Notes - Computer Vision MT25, Convolutions^U
• Notes - Computer Vision MT25, Filtering^U
• Notes - Computer Vision MT25, Fourier transform^U
• Notes - Computer Vision MT25, Image restoration^U
• Notes - Computer Vision MT25, Correspondences^U
• Notes - Computer Vision MT25, Scale-invariant feature transform^U
• Notes - Computer Vision MT25, Image classification^U
• Notes - Computer Vision MT25, Neural networks^U
• Notes - Computer Vision MT25, Loss function design^U
• Notes - Computer Vision MT25, Convolutional neural networks^U
• Notes - Computer Vision MT25, Dropout^U
• Notes - Computer Vision MT25, Learning curves^U
• Notes - Computer Vision MT25, Attention and transformers^U
• Notes - Computer Vision MT25, Interpreting vision models^U
• Notes - Computer Vision MT25, Object detection^U
• Notes - Computer Vision MT25, Precision and recall^U
• Notes - Computer Vision MT25, Segmentation^U
• Notes - Computer Vision MT25, Video^U
• Notes - Computer Vision MT25, Optical flow^U
• Notes - Computer Vision MT25, Visual tracking^U
• Notes - Computer Vision MT25, Lucas-Kanade tracking^U
• Notes - Computer Vision MT25, Camera models^U
• Notes - Computer Vision MT25, Multiple view geometry^U
• Notes - Computer Vision MT25, Neural rendering^U
• Notes - Computer Vision MT25, Generative models^U
• Notes - Computer Vision MT25, Representation learning^U
• Notes - Computer Vision MT25, Unsupervised computer vision^U
• Notes - Computer Vision MT25, Vision and language^U
• Notes - Computer Vision MT25, Ethics and privacy^U

Related notes

The majority of Course - Machine Learning MT23^U is relevant, but especially:

• Notes - Machine Learning MT23, Classification^U
• Notes - Machine Learning MT23, Clustering^U
• Notes - Machine Learning MT23, Convolutional neural networks^U
• Notes - Machine Learning MT23, Cross-entropy loss^U
• Notes - Machine Learning MT23, Generative models^U
• Notes - Machine Learning MT23, Linear regression^U
• Notes - Machine Learning MT23, Logistic regression^U
• Notes - Machine Learning MT23, Matrix calculus^U
• Notes - Machine Learning MT23, Maximum likelihood principle^U
• Notes - Machine Learning MT23, Naïve Bayes classifiers^U
• Notes - Machine Learning MT23, Neural networks^U
• Notes - Machine Learning MT23, Perceptrons^U
• Notes - Machine Learning MT23, Principal component analysis^U
• Notes - Machine Learning MT23, Support vector machines^U
• Notes - Machine Learning MT23, k-means clustering^U
• Notes - Machine Learning MT23, k-nearest neighbours^U
• Paper - Attention Is All You Need (2017)^U

Surprisingly, there is a small amount of overlap with the content covered in

• Notes - Complex Analysis MT23, Extended complex plane^U
• Notes - Complex Analysis MT23, Möbius maps^U

when it comes to homogenous coordinates and the projective line model of the complex plane.

Problem Sheets

• Sheet 1 (old), redacted^?
• Sheet 2 (old), redacted^?
• Sheet 3 (old), redacted^?
• Sheet 4 (old), redacted^?

To-Do List

Priority gaps

Priority 1 (exam-tested or central bookwork)

Priority 2 (clean bookwork from slides)

Priority 3 (slide content, lower exam frequency)

---

Related posts

• Notes - Computer Vision MT25, Video^U

  (incoming)
• Notes - Computer Vision MT25, Image representation^U

  (incoming)
• Notes - Computer Vision MT25, Convolutional neural networks^U

  (incoming)
• Notes - Computer Vision MT25, Object detection^U

  (incoming)
• Notes - Computer Vision MT25, Neural rendering^U

  (incoming)
• Notes - Computer Vision MT25, Convolutions^U

  (incoming)
• Notes - Computer Vision MT25, Visual tracking^U

  (incoming)
• Notes - Computer Vision MT25, Lucas-Kanade tracking^U

  (incoming)
• Notes - Computer Vision MT25, Segmentation^U

  (incoming)
• Notes - Computer Vision MT25, Sampling and reconstruction^U

  (incoming)
• Notes - Computer Vision MT25, Neural networks^U

  (incoming)
• Notes - Computer Vision MT25, Image restoration^U

  (incoming)
• Notes - Computer Vision MT25, Representation learning^U

  (incoming)
• Notes - Computer Vision MT25, Unsupervised computer vision^U

  (incoming)
• Notes - Computer Vision MT25, Correspondences^U

  (incoming)
• Notes - Computer Vision MT25, Homogenous coordinates and homographies^U

  (incoming)
• Notes - Computer Vision MT25, Subsampling and upsampling^U

  (incoming)
• Notes - Computer Vision MT25, Image transformations^U

  (incoming)
• Notes - Computer Vision MT25, Image classification^U

  (incoming)
• Notes - Computer Vision MT25, Filtering^U

  (incoming)
• Notes - Computer Vision MT25, Multiple view geometry^U

  (incoming)
• Notes - Computer Vision MT25, Interpreting vision models^U

  (incoming)
• Notes - Computer Vision MT25, Ethics and privacy^U

  (incoming)
• Notes - Computer Vision MT25, Precision and recall^U

  (incoming)
• Notes - Computer Vision MT25, Vision and language^U

  (incoming)
• Notes - Computer Vision MT25, Loss function design^U

  (incoming)
• Notes - Computer Vision MT25, Scale-invariant feature transform^U

  (incoming)
• Notes - Computer Vision MT25, Fourier transform^U

  (incoming)
• Notes - Computer Vision MT25, Attention and transformers^U

  (incoming)
• Notes - Computer Vision MT25, Learning curves^U

  (incoming)
• Notes - Computer Vision MT25, Dropout^U

  (incoming)
• Notes - Computer Vision MT25, Optical flow^U

  (incoming)
• Notes - Computer Vision MT25, Generative models^U

  (incoming)
• Notes - Computer Vision MT25, Camera models^U

  (incoming)
• Notes - Computer Vision MT25, Overview of results and methods^U

  (incoming)
• Part C^U

  (incoming)
• University Notes^U

  (incoming)
• Courses MT25^U

  (incoming)
• Course - Probability MT25^U

  (sim: 0.738)
• Course - Geometric Deep Learning HT26^U

  (sim: 0.656)
• Course - Continuous Optimisation HT26^U

  (sim: 0.611)
• Course - Artificial Intelligence MT24^U

  (sim: 0.588)
• Paper - Attention Is All You Need (2017)^U

  (incoming)