Visual Computing

Abstract

This course acquaints students with core knowledge in computer graphics, vision and learning. Topics include: Graphics pipeline, perception and camera models, transformation, shading, global illumination, texturing, sampling, filtering, edge detection, Bayes decision theory, classification, support vector machines, dimensionality reduction, clustering, Bayes nets.

Objective

This course provides an in-depth introdcution to the core concepts of computer graphics, computer vision, image processing, and machine learning. The course forms a basis for the specialization track Visual Computing of the CS master program at ETH.

Content

Course topics will include: Graphics pipeline, perception and color models, camera models, transformations and projection, projections, lighting, shading, global illumination, texturing, sampling theorem, Fourier transforms, convolution, linear filtering, diffusion, nonlinear filtering, edge detection, shape from X, stochastic image models, Bayes decision theory and classification, support vector machines, dimensionality reduction, clustering, Bayes nets In theoretical and practical homework assignments students will learn to apply and implement the presented concepts and algorithms.

Resources