Content

In this course, "computer vision" will primarily focus on the recognition of objects or events in images. The lecture will be split into classical CV algorithms and modern solutions based on neural networks. 

1.Introduction
2.Edge Detectors
3.Histograms
4.Optic flow
5.Hough Transform
6.SIFT / SURF
7.Introduction to Neural Information Processing
8.Convolutional Neural Networks
9.Image Classification, Object Detection
10.Semantic Segmentation
11.Pose Estimation
12.Vision Transformers
13.Recurrent Neural Networks, Image Captioning
14.Generative Models
15.Unsupervised feature extraction
 

Lecture Format

Lecture videos in English will be uploaded to YouTube and we will discuss the content and answer your questions on Wednesday, 10 - 12 am. 
 
 

Lecture Videos

We will upload new lectures to this playlist:

https://www.youtube.com/playlist?list=PLs7Vp-pCDX7yrUmgkxAEdNcgriOU6IBg5 

Lecture PDFs

You can download the lecture PDFs for your convenience here: 

https://drive.google.com/drive/folders/1rhSOIYs2kaET4aW0LLmv8CeqqmRwfpGK?usp=sharing

We would like you to give us feedback on typos, errors, weird formulations and anything else that needs to be changed. If you own a google account you can comment directly on the slides. Thank you!

Link to the Assignments repository

 
Invitation Link for Eduflow (Peer review platform)
 
 
Please upload your bi-weekly solutions here as well (also once per group). When all solutions are uploaded, another group will review your solution. You should therefore review one submission yourself.