“Elements of style: learning perceptual shape style similarity”

  • ©Zhaoliang Lun, Evangelos Kalogerakis, and Alla Sheffer

Conference:


Type:


Title:

    Elements of style: learning perceptual shape style similarity

Session/Category Title: Shape Analysis


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    The human perception of stylistic similarity transcends structure and function: for instance, a bed and a dresser may share a common style. An algorithmically computed style similarity measure that mimics human perception can benefit a range of computer graphics applications. Previous work in style analysis focused on shapes within the same class, and leveraged structural similarity between these shapes to facilitate analysis. In contrast, we introduce the first structure-transcending style similarity measure and validate it to be well aligned with human perception of stylistic similarity. Our measure is inspired by observations about style similarity in art history literature, which point to the presence of similarly shaped, salient, geometric elements as one of the key indicators of stylistic similarity. We translate these observations into an algorithmic measure by first quantifying the geometric properties that make humans perceive geometric elements as similarly shaped and salient in the context of style, then employing this quantification to detect pairs of matching style related elements on the analyzed models, and finally collating the element-level geometric similarity measurements into an object-level style measure consistent with human perception. To achieve this consistency we employ crowdsourcing to quantify the different components of our measure; we learn the relative perceptual importance of a range of elementary shape distances and other parameters used in our measurement from 50K responses to cross-structure style similarity queries provided by over 2500 participants.We train and validate our method on this dataset, showing it to successfully predict relative style similarity with near 90% accuracy based on 10-fold cross-validation.

References:


    1. Andrew, G., and Gao, J. 2007. Scalable training of l1-regularized log-linear models. In International Conference on Machine Learning. Google ScholarDigital Library
    2. Asafi, S., Goren, A., and Cohen-Or, D. 2013. Weak convex decomposition by lines-of-sight. In Proc. SGP. Google ScholarDigital Library
    3. Aucouturier, J., and Pachet, F. 2002. Music similarity measures: Whats the use. In SMIR.Google Scholar
    4. Ballard, D. H. 1987. Readings in computer vision: Issues, problems, principles, and paradigms. ch. Generalizing the Hough Transform to Detect Arbitrary Shapes. Google ScholarDigital Library
    5. Bell, R. M., and Koren, Y. 2007. Lessons from the netflix prize challenge. SIGKDD Explor. Newsl. 9, 2. Google ScholarDigital Library
    6. Besl, P. J., and McKay, N. D. 1992. A method for registration of 3-d shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14, 2. Google ScholarDigital Library
    7. Blumenson, J. J. G. 1995. Identifying American Architecture: A Pictorial Guide to Styles and Terms, 1600–1945.Google Scholar
    8. Bonneel, N., Sunkavalli, K., Paris, S., and Pfister, H. 2013. Example-based video color grading. ACM Trans. on Graph. 32, 4. Google ScholarDigital Library
    9. Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., and Hullender, G. 2005. Learning to rank using gradient descent. In Proc. ICML. Google ScholarDigital Library
    10. Chen, D.-Y., Tian, X.-P., Shen, Y.-T., and Ouhyoung, M. 2003. On visual similarity based 3D model retrieval. Computer Graphics Forum 22, 3.Google ScholarCross Ref
    11. Chen, X., Saparov, A., Pang, B., and Funkhouser, T. 2012. Schelling points on 3d surface meshes. ACM Trans. Graph. 31, 4. Google ScholarDigital Library
    12. Comaniciu, D. 2003. An algorithm for data-driven bandwidth selection. IEEE Trans. Pattern Anal. Mach. Intell. 25, 2. Google ScholarDigital Library
    13. Connected Lines, 2014. Period furniture style guide. http://www:connectedlines:com/styleguide/index:htm.Google Scholar
    14. Curtis, F. E., and Overton, M. L. 2012. A Sequential Quadratic Programming Algorithm for Nonconvex, Nonsmooth Constrained Optimization. SIAM Journal on Optimization 22, 2.Google ScholarCross Ref
    15. Doersch, C., Singh, S., Gupta, A., Sivic, J., and Efros, A. A. 2012. What makes Paris look like Paris? ACM Trans. Graph. 31, 4. Google ScholarDigital Library
    16. Fu, H., Cohen-Or, D., Dror, G., and Sheffer, A. 2008. Upright orientation of man-made objects. ACM Trans. Graph. 27, 3. Google ScholarDigital Library
    17. Garces, E., Agarwala, A., Gutierrez, D., and Hertzmann, A. 2014. A similarity measure for illustration style. ACM Trans. Graph. 33, 4. Google ScholarDigital Library
    18. Greig, D. M., Porteous, B. T., and Seheult, A. H. 1989. Exact maximum a posteriori estimation for binary images. Journal of the Royal Statistical Society 51, 2.Google Scholar
    19. Hertzmann, A., Jacobs, C. E., Oliver, N., Curless, B., and Salesin, D. H. 2001. Image analogies. In SIGGRAPH. Google ScholarDigital Library
    20. Huang, Q., Koltun, V., and Guibas, L. 2011. Joint shape segmentation with linear programming. ACM Trans. Graph. 30, 6. Google ScholarDigital Library
    21. Huang, Q.-X., Su, H., and Guibas, L. 2013. Fine-grained semi-supervised labeling of large shape collections. ACM Trans. Graph. 32, 6. Google ScholarDigital Library
    22. Hurtut, T., Gousseau, Y., Cheriet, F., and Schmitt, F. 2011. Artistic line-drawings retrieval based on the pictorial content. J. Comput. Cult. Herit. 4, 1. Google ScholarDigital Library
    23. Johnson, A. E., and Hebert, M. 1999. Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Trans. Pattern Anal. Mach. Intell. 21, 5. Google ScholarDigital Library
    24. Kalogerakis, E., Hertzmann, A., and Singh, K. 2010. Learning 3D mesh segmentation and labeling. ACM Trans. Graphics 29, 4. Google ScholarDigital Library
    25. Kalogerakis, E., Chaudhuri, S., Koller, D., and Koltun, V. 2012. A probabilistic model for component-based shape synthesis. ACM Trans. Graph. 31, 4. Google ScholarDigital Library
    26. Kim, V. G., Li, W., Mitra, N. J., Chaudhuri, S., Diverdi, S., and Funkhouser, T. 2013. Learning part-based templates from large collections of 3d shapes. ACM Trans. Graph. 32, 4. Google ScholarDigital Library
    27. Leifman, G. 2012. Surface regions of interest for viewpoint selection. In CVPR. Google ScholarDigital Library
    28. Lewis, A. S., and Overton, M. L. 2013. Nonsmooth optimization via quasi-newton methods. Math. Program. 141, 1–2.Google ScholarCross Ref
    29. Lewis, M. 2008. Architectura: elements of architectural style. Barrons Educational Series.Google Scholar
    30. Li, H., Zhang, H., Wang, Y., Cao, J., Shamir, A., and Cohen-Or, D. 2013. Curve style analysis in a set of shapes. Computer Graphics Forum 32, 6. Google ScholarDigital Library
    31. Liu, T., Hertzmann, A., Li, W., and Funkhouser, T. 2015. Style compatibility for 3d furniture models. ACM Trans. Graphics, to appear 34, 4. Google ScholarDigital Library
    32. Ma, C., Huang, H., Sheffer, A., Kalogerakis, E., and Wang, R. 2014. Analogy-driven 3D style transfer. Computer Graphics Forum 33, 2. Google ScholarDigital Library
    33. Mitra, N. J., Guibas, L. J., and Pauly, M. 2006. Partial and approximate symmetry detection for 3d geometry. ACM Trans. Graph. 25, 3. Google ScholarDigital Library
    34. Nocedal, J., and Wright, S. J. 2006. Numerical Optimization.Google Scholar
    35. Nutting, W. 1928. Furniture Treasury.Google Scholar
    36. Osada, R., Funkhouser, T., Chazelle, B., and Dobkin, D. 2002. Shape distributions. ACM Trans. Graph. 21, 4. Google ScholarDigital Library
    37. Schmidt, M., Fung, G., and Rosales, R. 2007. Fast optimization methods for l1 regularization: A comparative study and two new approaches. In Proc. ECML. Google ScholarDigital Library
    38. Shapira, L., Shamir, A., and Cohen-Or, D. 2008. Consistent mesh partitioning and skeletonisation using the shape diameter function. The Visual Computer 24, 4. Google ScholarDigital Library
    39. Shtrom, E., Leifman, G., and Tal, A. 2013. Saliency detection in large point sets. In Proc. ICCV. Google ScholarDigital Library
    40. Tenenbaum, J. B., and Freeman, W. T. 2000. Separating style and content with bilinear models. Neural Comput. 12, 6. Google ScholarDigital Library
    41. Tenenbaum, J., Silva, V., and Langford, J. 2000. A global geometric framework for nonlinear dimensionality reduction. Science 290, 5500.Google ScholarCross Ref
    42. Tibshirani, R. 1996. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society 58.Google Scholar
    43. van Kaick, O., Xu, K., Zhang, H., Wang, Y., Sun, S., Shamir, A., and Cohen-Or, D. 2013. Co-hierarchical analysis of shape structures. ACM Trans. on Graphics 32, 4. Google ScholarDigital Library
    44. van Kaick, O., Fish, N., Kleiman, Y., Asafi, S., and Cohen-Or, D. 2014. Shape segmentation by approximate convexity analysis. ACM Trans. on Graph. 34, 1. Google ScholarDigital Library
    45. Willats, J., and Durand, F. 2005. Defining pictorial style: lessons from linguistics and computer graphics. Axiomathes 15.Google Scholar
    46. Xu, K., Li, H., Zhang, H., Cohen-Or, D., Xiong, Y., and Cheng, Z.-Q. 2010. Style-content separation by anisotropic part scales. ACM Trans. Graph. 29, 6. Google ScholarDigital Library
    47. Yumer, M., and Kara, L. 2014. Co-constrained handles for deformation in shape collections. ACM Trans. Graph. 32, 6. Google ScholarDigital Library


ACM Digital Library Publication:



Overview Page: