“Approximate Translational Building Blocks for Image Decomposition and Synthesis” by Li and Wand

  • ©

Conference:


Type(s):


Title:

    Approximate Translational Building Blocks for Image Decomposition and Synthesis

Session/Category Title:   INTRINSIC IMAGES

Presenter(s)/Author(s):


Moderator(s):


Abstract:


    We introduce approximate translational building blocks for unsupervised image decomposition. Such building blocks are frequently appearing copies of image patches that are mapped coherently under translations.

    We exploit the coherency assumption to find approximate building blocks in noisy and ambiguous image data, using a spectral embedding of re-occurrence patterns. We quantitatively evaluate our method on a large benchmark dataset and obtain clear improvements over state-of-the-art methods. We apply our method to texture synthesis by integrating building block constraints and their offset statistics into a conventional Markov random field model. A user study shows improved retargeting results even if the images are only partially described by a few classes of building blocks.

References:


    1. H. Agrawal and A. M. Namboodiri. 2012. Detection and segmentation of approximable repetitive patterns in relief images. In Proceedings of the 8th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP’12). 1–8. Google ScholarDigital Library
    2. F. Bao, M. Schwarz, and P. Wonka. 2013. Procedural façade variations from a single layout. ACM Trans. Graph. 32, 1, 8:1–8:13. Google ScholarDigital Library
    3. C. Barnes, E. Shechtman, A. Finkelstein, and D. B. Goldman. 2009. PatchMatch: A randomized correspondence algorithm for structured image editing. ACM Trans. Graph. 28, 3, 24:1–24:11. Google ScholarDigital Library
    4. M. Bokeloh, A. Berner, M. Wand, H.-P. Seidel, and A. Schilling. 2009. Symmetry detection using fracture lines. Comput. Graph. Forum 28, 2, 697–706.Google ScholarCross Ref
    5. Y. Boykov, O. Versler, and R. Zabih. 2001. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 11, 1222–1239. Google ScholarDigital Library
    6. M.-M. Cheng, F.-L. Zhang, N. J. Mitra, X. Huang, and S.-M. Hu. 2010. RepFinder: Finding approximately repeated scene elements for image editing. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’10). ACM Press, New York, 82:1–82:8. Google ScholarDigital Library
    7. M. Cho, Y. M. Shin, and K. M. Lee. 2010. Unsupervised detection and segmentation of identical objects. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recgonition (CVPR’10). 1617–1624.Google Scholar
    8. D. Dai, H. Riemenschneider, G. Schmitt, and L. Van Gool. 2013. Example-based façade texture synthesis. In Proceedings of the International Conference on Computer Vision (ICCV’13). 1065–1072. Google ScholarDigital Library
    9. N. Dalal and B. Triggs. 2005. Histograms of oriented gradients for human detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’05). 886–893. Google ScholarDigital Library
    10. J.-M. Dischler, K. M. B. Lvy, and D. Ghazanfarpour. 2002. Texture particles. Comput. Graph. Forum 21, 3, 401–410.Google ScholarCross Ref
    11. A. A. Efros and T. K. Leung. 1999. Texture synthesis by nonparametric sampling. In Proceedings of the International Conference on Computer Vision (ICCV’99). 1033–1038. Google ScholarDigital Library
    12. R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. 2008. LIBLINEAR: A library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874. Google ScholarDigital Library
    13. P. F. Felenzenszwald, R. B. Girshick, D. Mcallester, and D. Ramanan. 2010. Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Learn. 32, 9, 1627–1645. Google ScholarDigital Library
    14. J. Gao, Y. Hu, J. Liu, and R. Yang. 2009. Unsupervised learning of high-order structural semantics from images. In Proceedings of the International Conference on Computer Vision (ICCV’09). 2122–2129.Google Scholar
    15. J. Hays, M. Leordeanu, A. A. Efros, and Y. Liu. 2006. Discovering texture regularity as a higher-order correspondence problem. In Proceedings of the European Conference on Computer Vision (ECCV’06). 522–535. Google ScholarDigital Library
    16. K. He and J. Sun. 2012. Statistics of patch offsets for image completion. In Proceedings of the European Conference on Computer Vision (ECCV’12). 16–29. Google ScholarDigital Library
    17. A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, and D. H. Salesin. 2001. Image analogies. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’01). ACM Press, New York, 327–340. Google ScholarDigital Library
    18. S.-M. Hu, F.-L. Zhang, M. Wang, R. R. Martin, and J. Wang. 2013. PatchNet: A patch-based image representation for interactive library-driven image editing. ACM Trans. Graph. 32, 6, 196:1–196:12. Google ScholarDigital Library
    19. Q. Huang, L. Guibas, and N. J. Mitra. 2013. Near-regular structure discovery using linear programming. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’13). ACM Press, New York.Google Scholar
    20. J. Kalojanov, M. Bokeloh, M. Wand, L. Guibas, H.-P. Seidel, and P. Slusallek. 2012. MicroTiles: Extracting building blocks from correspondences. Comput. Graph. Forum 31, 1597–1606. Google ScholarDigital Library
    21. T. Kobayashi and N. Otsu. 2008. Image feature extraction using gradient local auto-correlations. In Proceedings of the European Conference on Computer Vision (ECCV’08). 346–358. Google ScholarDigital Library
    22. V. Kwatra, I. Essa, A. Bobick, and N. Kwatra. 2005. Texture optimization for example-based synthesis. ACM Trans. Graph. 24, 3, 795–802. Google ScholarDigital Library
    23. V. Kwatra, A. Schodl, I. Essa, G. Turk, and A. Bobick. 2003. Graphcut textures: Image and video synthesis using graph cuts. ACM Trans. Graph. 22, 3, 277–286. Google ScholarDigital Library
    24. P.-E. Landes and C. Soler. 2009. Content-aware texture synthesis. Tech. rep. RR-6959, INRIA. June.Google Scholar
    25. Q. Le, M. Ranzato, R. Monga, M. Devin, K. Chen, G. Corrado, J. Dean, and A. Ng. 2012. Building high-level features using large scale unsupervised learning. In Proceedings of the International Conference on Machine Learning (ICML’12).Google Scholar
    26. S. Lee and Y. Liu. 2010. Skewed rotation symmetry group detection. IEEE Trans. Pattern Anal. Mach. Intell. 32, 9, 1659–1672. Google ScholarDigital Library
    27. S. Lefebvre and H. Hoppe. 2006. Appearance-space texture synthesis. ACM Trans. Graph. 25, 3, 541–548. Google ScholarDigital Library
    28. T. K. Leung and J. Malik. 1996. Detecting, localizing and grouping repeated scene elements from an image. In Proceedings of the European Conference on Computer Vision (ECCV’96). 546–555. Google ScholarDigital Library
    29. W.-C. Lin, J. Hays, C. Wu, Y. Liu, and V. Kwatra. 2006. Quantitative evaluation of near regular texture synthesis algorithms. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’06). 427–434. Google ScholarDigital Library
    30. Y. Lipman, X. Chen, I. Daubechies, and T. Funkhouser. 2010. Symmetry factored embedding and distance. ACM Trans. Graph. 29, 103:1–103:12. Google ScholarDigital Library
    31. J. Liu and Y. Liu. 2013. Grasp recurring patterns from a single view. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’13). 2003–2010. Google ScholarDigital Library
    32. Y. Liu, W.-C. Lin, and J. Hays. 2004. Near-regular texture analysis and manipulation. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’04). ACM Press, New York, 368–376. Google ScholarDigital Library
    33. C. Ma, L.-Y. Wei, S. Lefebvre, and X. Tong. 2013. Dynamic element textures. ACM Trans. Graph. 32, 4, 90:1–90:10. Google ScholarDigital Library
    34. C. Ma, L.-Y. Wei, and X. Tong. 2011. Discrete element textures. ACM Trans. Graph. 30, 4, 62:1-62:10. Google ScholarDigital Library
    35. A. Martinovic, M. Mathias, J. Weissenberg, and L. J. Van Gool. 2012. A three-layered approach to façade parsing. In Proceedings of the European Conference on Computer Vision (ECCV’12). 416–429. Google ScholarDigital Library
    36. N. J. Mitra, L. J. Guibas, and M. Pauly. 2006. Partial and approximate symmetry detection for 3D geometry. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’06). ACM Press, New York, 560–568. Google ScholarDigital Library
    37. M. Pauly, N. J. Mitra, J. Wallner, H. Pottmann, and L. Guibas. 2008. Discovering structural regularity in 3D geometry. ACM Trans. Graph. 27, 3, 43:1–43:11. 
    38. Y. Pritch, E. Kav-Venaki, and S. Peleg. 2009. Shift-map image editing. In Proceedings of the International Conference on Computer Vision (ICCV’09). 151–158.
    39. A. Rosenberger, D. Cohen-Or, and D. Lischinski. 2009. Layered shape synthesis: Automatic generation of control maps for non-stationary textures. ACM Trans. Graph. 28, 5, 107:1–107:9. 
    40. F. Schaffalitzky and A. Zisserman. 1998. Geometric grouping of repeated elements within images. http://cronos.rutgers.edu/∼meer/TEACHTOO/PAPERS/schaffalitzky99.pdf.
    41. E. Shechtman and M. Irani. 2007. Matching local self-similarities across images and videos. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’07).
    42. D. Simakov, Y. Caspi, E. Shechtman, and M. Irani. 2008. Summarizing visual data using bidirectional similarity. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’08).
    43. S. Singh, A. Gupta, and A. A. Efros. 2012. Unsupervised discovery of mid-level discriminative patches. In Proceedings of the European Conference on Computer Vision (ECCV’12). 73–86. 
    44. C.-L. Tai. 2012. Parsing façade with rank-one approximation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’12). 1720–1727. 
    45. O. Teboul, I. Kokkinos, L. Simon, P. Koutsourakis, and N. Paragios. 2011. Shape grammar parsing via reinforcement learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11). 2273–2280. 
    46. H. Wang, Y. Wexler, E. Ofek, and H. Hoppe. 2008. Factoring repeated content within and among images. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’08). ACM Press, New York, 14:1–14:10. 
    47. L.-Y. Wei, S. Lefebvre, V. Kwatra, and G. Turk. 2009. State of the art in example-based texture synthesis. In Proceedings of the Eurographics State of the Art Report (EG-STAR’09). 93–117.
    48. L.-Y. Wei and M. Levoy. 2000. Fast texture synthesis using tree-structured vector quantization. In Proceedings of the Annual ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’00). ACM Press, New York, 479–488. 
    49. C. Wu, J.-M. Frahm, and M. Pollefeys. 2010a. Detecting large repetitive structures with salient boundaries. In Proceedings of the European Conference on Computer Vision (ECCV’10). Vol. 6312. 142–155. 
    50. H. Wu, Y.-S. Wang, K.-C. Feng, T.-T. Wong, T.-Y. Lee, and P.-A. Heng. 2010b. Resizing by symmetry-summarization. ACM Trans. Graph. 29, 6. 
    51. H. Zhang, K. Xu, W. Jiang, J. Lin, D. Cohen-Or, and B. Chen. 2013. Layered analysis of irregular facades via symmetry maximization. ACM Trans. Graph. 32, 4, 104:1–104:10. 
    52. P. Zhao and L. Quan. 2011. Translation symmetry detection in a fronto-parallel view. In Proccedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’11). 1009–1016.

ACM Digital Library Publication:


Overview Page: