Dive into a comprehensive 15-hour course on Computer Vision offered by Eberhard Karls University of Tübingen. Explore the fundamentals of image formation, structure-from-motion techniques, stereo reconstruction methods, and probabilistic graphical models. Learn about the history of computer vision, geometric and photometric image formation, and image sensing pipelines. Discover advanced topics such as two-frame structure-from-motion, bundle adjustment, block matching, and Siamese networks for stereo reconstruction. Gain insights into Markov Random Fields, factor graphs, and belief propagation in probabilistic graphical models. Apply these concepts to real-world problems like multi-view reconstruction and optical flow. Investigate shape-from-X techniques, including shape-from-shading, photometric stereo, and volumetric fusion. Master parameter estimation and deep structured models in graphical model learning.
Overview
Syllabus
Computer Vision - Lecture 1.1 (Introduction: Organization).
Computer Vision - Lecture 1.2 (Introduction: Introduction).
Computer Vision - Lecture 1.3 (Introduction: History of Computer Vision).
Computer Vision - Lecture 2.1 (Image Formation: Primitives and Transformations).
Computer Vision - Lecture 2.2 (Image Formation: Geometric Image Formation).
Computer Vision - Lecture 2.3 (Image Formation: Photometric Image Formation).
Computer Vision - Lecture 2.4 (Image Formation: Image Sensing Pipeline).
Computer Vision - Lecture 3.1 (Structure-from-Motion: Preliminaries).
Computer Vision - Lecture 3.2 (Structure-from-Motion: Two-frame Structure-from-Motion).
Computer Vision - Lecture 3.3 (Structure-from-Motion: Factorization).
Computer Vision - Lecture 3.4 (Structure-from-Motion: Bundle Adjustment).
Computer Vision - Lecture 4.1 (Stereo Reconstruction: Preliminaries).
Computer Vision - Lecture 4.2 (Stereo Reconstruction: Block Matching).
Computer Vision - Lecture 4.3 (Stereo Reconstruction: Siamese Networks).
Computer Vision - Lecture 4.4 (Stereo Reconstruction: Spatial Regularization).
Computer Vision - Lecture 4.5 (Stereo Reconstruction: End-to-End Learning).
Computer Vision - Lecture 5.1 (Probabilistic Graphical Models: Structured Prediction).
Computer Vision - Lecture 5.2 (Probabilistic Graphical Models: Markov Random Fields).
Computer Vision - Lecture 5.3 (Probabilistic Graphical Models: Factor Graphs).
Computer Vision - Lecture 5.4 (Probabilistic Graphical Models: Belief Propagation).
Computer Vision - Lecture 5.5 (Probabilistic Graphical Models: Examples).
Computer Vision - Lecture 6.1 (Applications of Graphical Models: Stereo Reconstruction).
Computer Vision - Lecture 6.2 (Applications of Graphical Models: Multi-View Reconstruction).
Computer Vision - Lecture 6.3 (Applications of Graphical Models: Optical Flow).
Computer Vision - Lecture 7.1 (Learning in Graphical Models: Conditional Random Fields).
Computer Vision - Lecture 7.2 (Learning in Graphical Models: Parameter Estimation).
Computer Vision - Lecture 7.3 (Learning in Graphical Models: Deep Structured Models).
Computer Vision - Lecture 8.1 (Shape-from-X: Shape-from-Shading).
Computer Vision - Lecture 8.2 (Shape-from-X: Photometric Stereo).
Computer Vision - Lecture 8.3 (Shape-from-X: Shape-from-X).
Computer Vision - Lecture 8.4 (Shape-from-X: Volumetric Fusion).
Taught by
Tübingen Machine Learning
