Multidimensional visual texture is the appropriate paradigm for physically correct material visual properties representation. The course will present recent advances in texture modelling methodology as applied in computer vision, pattern recognition, computer graphics, and virtual/augmented reality applications. Contrary to previous courses on material appearance, we will focus on materials whose nature allows the exploitation of texture modeling approaches. This topic is introduced in the wider and complete context of pattern recognition and image processing. It comprehends modeling of multi-spectral images and videos which can be accomplished either with multidimensional mathematical models or sophisticated sampling methods from the original measurements. The key aspects of the topic, i.e. different multidimensional data models with their corresponding benefits and drawbacks, optimal model selection, parameter estimation and model synthesis techniques, are discussed. These methods produce compact parametric sets that not only faithfully reproduce material appearance, but are also vital for visual scene analysis, e.g. texture segmentation, classification, and retrieval. Special attention is devoted to recent advanced trends towards Bidirectional Texture Function (BTF) modeling, used for materials that do not obey Lambertian law, and whose reflectance has non-trivial illumination and viewing direction dependency. BTFs represent the best known effectively applicable textural representation of most real-world materials’ visual properties. The techniques covered include efficient Markov random field-based algorithms, intelligent sampling algorithms, spatially-varying reflectance models and challenges with their possible implementation on GPU. The course also deals with proper data measurement, visualization of texture models in virtual scenes, visual quality evaluation feedback, as well as description of key industrial and research applications. We will discuss options as to which type of material representation is appropriate for required application, what are its limits and possible modelling options, and what the biggest challenges in realistic modelling of materials are.

Level
Intermediate

Intended Audience
The tutorial will start with basic principles and will build on fundamentals to discuss the latest techniques for texture modeling. It will be suitable for newcomers as well as practitioners who wish to be brought up to date on state-of-the-art methodology of texture modeling.

Prerequisites
Participants are expected to possess graduate level statistics knowledge as well as knowledge of basic image processing and computer graphics principles.

Course Schedule
Session 1: 14:15-16:00
14:15-14:20 Michal Haindl: Introduction
14:20-14:35 Michal Haindl: Mathematical representation of material appearance
14:35-15:05 Jiri FIlip: Visual texture acquisition
15:05-15:40 Michal Haindl: Static mutispectral textures
15:40-16:00 Jiri Filip: From BRDF to spatially-varying BRDF

Break: 16:00-16:15

Session 2: 16:15-18:00
16:15-17:10 Michal Haindl, Jiri Filip: Bidirectional Texture Functions
17:10-17:45 Jiri Filip: Appearance visualizations & Perceptual validation
17:45-18:00 Michal Haindl: Applications, Open problems

Presenter(s)
Michal Haindl is a fellow of the International Association for Pattern Recognition (IAPR) and a Professor at the Institute of Information Theory and Automation (UTIA) of the Academy of Sciences of the Czech Republic. From 1983 to 1990, he worked at the UTIA. From 1990 to 1995, he was with the University of Newcastle; Rutherford Appleton Laboratory, Didcot; Centre for Mathematics and Computer Science, Amsterdam and Institute National de Recherche en Informatique et en Automatique, Rocquencourt. In 1995 he rejoined UTIA where he is now head of the Pattern Recognition department. His current research interests include random fields applications in pattern recognition, image processing and automatic acquisition of virtual reality models.

Jiri Filip received his MS and PhD in Cybernetics from the Czech Technical University in Prague. He is currently with the Pattern Recognition Department at the UTIA of the Academy of Sciences of the Czech Republic, Prague. He was a postdoctoral Marie Curie Research Fellow in the Texture Lab at the School of Mathematical and Computer Sciences, Heriot-Watt University. His current research is focused on measurement, analysis, modeling, and human perception of material appearance.