Labs and presentation of the Computer Vision 1 and Computer Vision 2 courses of the MSc in Artificial Intelligence at the University of Amsterdam. Labs in Computer Vision 1 are joint work with Gabriele Bani. For Computer Vision 2, work was done together with Gabriele Bani and Andreas Hadjipieri.
Problem statement and Solution
Face heightmap for different configurations
Problem statement and Solution
Gabor segmentation applied to images with and without smoothing
Problem statement and Solution
Corner detection with varying sigma and threshold
Feature Tracking
Problem statement and Solution
Original and stitched bus images
Final Project: Bag-of-Words based Image Classification (part 1) and Convolutional Neural Networks for Image Classification (part 2)
Problem statement for part 1, Problem statement for part 2 and Solution
Performance of Bag-of-Words model
T-SNE Visualizations of CNN model features
- Matlab 2017a
Problem statement and Solution
Result of Scene Merging
Problem statement and Solution
| Feature Matching | Point-View Matrices |
|---|---|
 |
 |
Result of the Structure from Motion algorithm
Problem statement and Solution
Reconstruction using Poisson with texture
To run each file, take a look at following files:
- Instructions for Lab 1.
- Instructions for Lab 2.
- Preparation section in Problem statement for Lab 3.
Paper Learning to Reason: End-to-End Module Networks for Visual Question Answering by Hu et al. is trying to tackle problem of question answering. As questions are inherently compositional, authors argue that they can be answered easier if decomposed into modular sub-problems. They propose End-to-End Module Networks, which learn to reason by directly predicting instance-specific network layouts without the aid of a parser.
Slides presenting paper can be found here.
Copyright © 2017-2018 Andrii Skliar.
This project is distributed under the MIT license. This was developed as part of the courses Computer Vision 1 and Computer Vision 2 taught by Theo Gevers at the University of Amsterdam. Please follow the UvA regulations governing Fraud and Plagiarism in case you are a student.