Home > Program > Tutorials > PM-04
ICPR2012 Tutorials PM-04
Advanced Nature Exteriors Modelling
Lecturer:
Abstract: A multidimensional visual texture is the appropriate paradigm for physically correct material visual properties representation. The course will present recent advances in texture modelling methodology applied in computer vision, pattern recognition, computer graphics, and virtual/augmented reality applications. This topic is introduced in wider and complete context of pattern recognition and image processing. It comprehends modelling of multi-spectral images and videos which can be accomplished either by a multi-dimensional mathematical models or sophisticated sampling methods from the original measurements. The key aspects of the topic, i.e., different multi-dimensional 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 allow not only to faithfully reproduce material appearance, but are also vital for visual scene analysis, e.g., texture segmentation, classification, retrieval etc. Special attention is devoted to a recent most advanced trend towards Bidirectional Texture Function (BTF) modelling, used for materials that do not obey Lambertian law, whose reflectance has non-trivial illumination and viewing direction dependency. BTFs recently represent the best known effectively applicable textural representation of the most real-world materials? visual properties. Introduced approaches will be categorized and compared in terms of visual quality, analysis and synthesis speed, texture compression rate, and their ability to be applied in 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. |
Course description
- Introduction (20 min.)
- - Motivation, texture definitions, photometry.
- Mathematical representation of material appearance (20 min.)
- Taxonomy of material representations (texture, BRDF, SVBRDF, BTF, etc. ).
- Visual texture acquisition (20 min.)
- Static mutispectral textures (30 min.)
- - Analysis and modelling approaches, synthesis.
- - Applications for visual scene analysis (segmentation, classification and retrieval, etc.).
- From BRDF to spatially-varying BRDF (20 min.)
- - Reflectance representation, compression, modelling.
- - Options and limitations of its spatial extension.
- Bidirectional Texture Functions (BTF) compression & modelling (50 min)
- - Compression approaches.
- - Modelling approaches.
- Appearance visualizations & Perceptual validation (30 min)
- Applications, Open problems & Challenges (15 min)
Relevant References:
[FCGH08] FILIP J., CHANTLER M. J., GREEN P. R., HAINDL M.: A psychophysically validated metric for bidirectional texture data reduction. ACM Transactions on Graphics (TOG) 27, 5 (December 2008), 138:1–138:11.
[FH07] FILIP J., HAINDL M.: BTF modelling using BRDF texels. International Journal of Computer Mathematics 84, 9 (2007), 1267 – 1283.
[FH09] FILIP J., HAINDL M.: Bidirectional texture function modeling: A state of the art survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 31, 11 (2009), 1921– 1940.
[HF10] HAINDL M., FILIP J.: Bidirectional texture function modelling. CVPR Tutorial, 2010. [HF11] HAINDL M., FILIP J.: Advanced textural representation of materials appearance. In SIGGRAPH Asia 2011 Courses (New York, NY, USA, 2011), SA ’11, ACM, pp. 1:1–1:84.
[HH05a] HAINDL M., HATKA M.: BTF Roller. In Texture 2005. Proceedings of the 4th International Workshop on Texture Analysis (Los Alamitos, October 2005), Chantler M., Drbohlav O., (Eds.), IEEE, pp. 89–94.
[HH05b] HAINDL M., HATKA M.: A roller – fast sampling-based texture synthesis algorithm. In Proceedings of the 13th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (Plzen, February 2005), Skala V., (Ed.), UNION Agency - Science Press, pp. 93–96.
About Lecturer:
MICHAL HAINDL, Professor (MSc. in Control Engineering, 1979, PhD in Cybernetics 1982, ScD in 2000 from the Czech Technical University), Fellow of the IAPR (2004) and SMIEEE. He is currently the Head of the Department of Pattern Recognition at the Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic and the professor at the Czech Technical University, Prague. In 1992 - 1998 and since 2009 he was and is the Governing Board member of IAPR (International Association for Pattern Recognition), He was Chairman of IAPR Publication and Publicity Committee, Chairman of IAPR Membership Committee and member of several other IAPR committees. Since 1995 he is editorial board member of ERCIM (European Research Consortium for Informatics and Mathematics), editorial board member of IJPRAI, Governing Board member of the Czech Society for Cybernetics and Informatics, Governing Board member of Czech Pattern Recognition Society, a senior member of IEEE. Between 1990 to 1995, he was a researcher fellow or senior researcher at the University of Newcastle, Newcastle; Rutherford Appleton Laboratory, Didcot; Centre for Mathematics and Computer Science, Amsterdam and Institute National de Recherche en Informatique et en Automatique, Rocquencourt working on severalimage analysis and pattern recognition projects. In 1995 he rejoined the Institute of Information Theory and Automation of the Czech Academy of Sciences. His present research interest concern random fields theory applications in pattern recognition and image processing. He is the author of about 280 research papers published in books, journals and conference proceedings.
JIŘÍ FILIP received the MSc in 2002 and PhD in 2006, both in cybernetics from the Czech Technical University in Prague. Since 2002 he is a researcher at the Institute of Information Theory and Automation at Academy of Sciences of the Czech Republic. Between 2008-2009 he was Marie Curie research fellow at School of Mathematical and Computer Sciences at Heriot-Watt University, Edinburgh. His current research is focused on analysis and synthesis of highdimensional texture data and its psychophysical aspects.
Archive: Call for Tutorial Proposals
