Recognizing Materials from Virtual Examples

  • Wenbin Li
  • Mario Fritz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7575)


Due to the strong impact of machine learning methods on visual recognition, performance on many perception task is driven by the availability of sufficient training data. A promising direction which has gained new relevance in recent years is the generation of virtual training examples by means of computer graphics methods in order to provide richer training sets for recognition and detection on real data. Success stories of this paradigm have been mostly reported for the synthesis of shape features and 3D depth maps. Therefore we investigate in this paper if and how appearance descriptors can be transferred from the virtual world to real examples. We study two popular appearance descriptors on the task of material categorization as it is a pure appearance-driven task. Beyond this initial study, we also investigate different approach of combining and adapting virtual and real data in order to bridge the gap between rendered and real-data. Our study is carried out using a new database of virtual materials VIPS that complements the existing KTH-TIPS material database.


Domain Adaptation Alignment Procedure Virtual Data Material Database Virtual Material 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipmanand, A., Blake, A.: Real-time human pose recognition in parts from a single depth image. In: CVPR (2011)Google Scholar
  2. 2.
    Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. IJCV 43, 29–44 (2001)zbMATHCrossRefGoogle Scholar
  3. 3.
    Varma, M., Zisserman, A.: A statistical approach to texture classification from single images. Int. J. Comput. Vision 62, 61–81 (2005)Google Scholar
  4. 4.
    Dana, K., van Ginneken, B.: Reflectance and texture of real-world surfaces. In: CVPR (1997)Google Scholar
  5. 5.
    Hayman, E., Caputo, B., Fritz, M., Eklundh, J.-O.: On the Significance of Real-World Conditions for Material Classification. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 253–266. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Caputo, B., Hayman, E., Mallikarjuna, P.: Class-specific material categorisation. In: ICCV (2005)Google Scholar
  7. 7.
    Sharan, L., Rosenholtz, R., Adelson, E.H.: Material perception: What can you see in a brief glance? Journal of Vision (2009)Google Scholar
  8. 8.
    Liu, C., Sharan, L., Adelson, E.H., Rosenholtz, R.: Exploring features in a bayesian framework for material recognition. In: CVPR (2010)Google Scholar
  9. 9.
    Decoste, D., Schölkopf, B.: Training invariant support vector machines. Mach. Learn. 46, 161–190 (2002)zbMATHCrossRefGoogle Scholar
  10. 10.
    Enzweiler, M., Gavrila, D.M.: A mixed generative-discriminative framework for pedestrian classification. In: CVPR (2008)Google Scholar
  11. 11.
    Pishchulin, L., Jain, A., Wojek, C., Andriluka, M., Thormaehlen, T., Schiele, B.: Learning people detection models from few training samples. In: CVPR (2011)Google Scholar
  12. 12.
    Targhi, A.T., Geusebroek, J.M., Zisserman, A.: Texture classification with minimal training images. In: IEEE International Conference on Pattern Recognition (2008)Google Scholar
  13. 13.
    Lai, K., Fox, D.: 3D laser scan classification using web data and domain adaptation. In: Proceedings of Robotics: Science and Systems (2009)Google Scholar
  14. 14.
    Wohlkinger, W., Vincze, M.: 3D object classification for mobile robots in home-environments using web-data. In: International Conference on Cognitive Systems, CogSys (2010)Google Scholar
  15. 15.
    Stark, M., Goesele, M., Schiele, B.: Back to the future: Learning shape models from 3D cad data. In: BMVC (2010)Google Scholar
  16. 16.
    Kaneva, B., Torralba, A., Freeman, W.: Evaluation of image features using a photorealistic virtual world. In: ICCV (2011)Google Scholar
  17. 17.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting Visual Category Models to New Domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  18. 18.
    Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In: CVPR (2011)Google Scholar
  19. 19.
    Davis, J., Kulis, B., Jain, P., Sra, S., Dhillon, I.: Information-theoretic metric learning. In: ICML (2007)Google Scholar
  20. 20.
    Daumé III, H.: Frustratingly easy domain adaptation. In: Conference of the Association for Computational Linguistics, ACL (2007)Google Scholar
  21. 21.
    Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recognition 29, 51–59 (1996)CrossRefGoogle Scholar
  22. 22.
    Zhang, J., Marszałek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: a comprehensive study. IJCV 73, 213–238 (2007)CrossRefGoogle Scholar
  23. 23.
    Chapelle, O., Haffner, P., Vapnik, V.: Svms for histogram-based image classification. IEEE Transactions on Neural Networks (1999)Google Scholar
  24. 24.
    Nillius, P., Eklundh, J.-O.: Classifying Materials from Their Reflectance Properties. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 366–376. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  25. 25.
    Wang, O., Gunawardane, P., Scher, S., Davis, J.: Material classification using brdf slices. In: CVPR (2009)Google Scholar
  26. 26.
    Liu, L., Fieguth, P., Kuang, G., Zha, H.: Sorted random projections for robust texture classification. In: ICCV (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Wenbin Li
    • 1
  • Mario Fritz
    • 1
  1. 1.Max Planck Institute for InformaticsSaarbruckenGermany

Personalised recommendations