“Single-view reconstruction via joint analysis of image and shape collections”

  • ©Qi-xing Huang, Hai Wang, and Vladlen Koltun

Conference:


Type:


Title:

    Single-view reconstruction via joint analysis of image and shape collections

Session/Category Title: Shape Analysis

Presenter(s)/Author(s):


Moderator(s):


Abstract:


    We present an approach to automatic 3D reconstruction of objects depicted in Web images. The approach reconstructs objects from single views. The key idea is to jointly analyze a collection of images of different objects along with a smaller collection of existing 3D models. The images are analyzed and reconstructed together. Joint analysis regularizes the formulated optimization problems, stabilizes correspondence estimation, and leads to reasonable reproduction of object appearance without traditional multi-view cues.

References:


    1. Aubry, M., Maturana, D., Efros, A., Russell, B., and Sivic, J. 2014. Seeing 3D chairs: Exemplar part-based 2D-3D alignment using a large dataset of CAD models. In CVPR. Google ScholarDigital Library
    2. Averbuch-Elor, H., Wang, Y., Qian, Y., Gong, M., Kopf, J., Zhang, H., and Cohen-Or, D. 2015. Distilled collections from textual image queries. Comput. Graph. Forum 34.Google Scholar
    3. Belongie, S., Malik, J., and Puzicha, J. 2002. Shape matching and object recognition using shape contexts. PAMI 24, 4. Google ScholarDigital Library
    4. Cameron, S., and Culley, R. 1986. Determining the minimum translational distance between two convex polyhedra. In ICRA.Google Scholar
    5. Carreira, J., Kar, A., Tulsiani, S., and Malik, J. 2015. Virtual view networks for object reconstruction. In CVPR.Google Scholar
    6. Carreira, J., Vicente, S., Agapito, L., and Batista, J. 2015. Lifting object detection datasets into 3D. PAMI. To appear.Google Scholar
    7. Chen, T., Zhu, Z., Shamir, A., Hu, S., and Cohen-Or, D. 2013. 3-Sweep: extracting editable objects from a single photo. ACM Trans. Graph. 32, 6. Google ScholarDigital Library
    8. Criminisi, A., Reid, I., and Zisserman, A. 2000. Single view metrology. IJCV 40, 2. Google ScholarDigital Library
    9. Dalal, N., and Triggs, B. 2005. Histograms of oriented gradients for human detection. In CVPR. Google ScholarDigital Library
    10. Debevec, P., Taylor, C., and Malik, J. 1996. Modeling and rendering architecture from photographs: A hybrid geometry- and image-based approach. In SIGGRAPH. Google ScholarDigital Library
    11. Eigen, D., Puhrsch, C., and Fergus, R. 2014. Depth map prediction from a single image using a multi-scale deep network. In NIPS.Google Scholar
    12. Fouhey, D., Gupta, A., and Hebert, M. 2013. Data-driven 3D primitives for single image understanding. In ICCV. Google ScholarDigital Library
    13. Gonzalez, T. F. 1985. Clustering to minimize the maximum intercluster distance. Theoretical Computer Science 38.Google Scholar
    14. Hartley, R., and Zisserman, A. 2000. Multiple View Geometry in Computer Vision. Cambridge University Press. Google ScholarDigital Library
    15. Huang, Q., Koltun, V., and Guibas, L. 2011. Joint shape segmentation with linear programming. ACM Trans. Graph. 30, 6. Google ScholarDigital Library
    16. 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
    17. Kar, A., Tulsiani, S., Carreira, J., and Malik, J. 2015. Category-specific object reconstruction from a single image. In CVPR.Google Scholar
    18. Kholgade, N., Simon, T., Efros, A., and Sheikh, Y. 2014. 3D object manipulation in a single photograph using stock 3D models. ACM Trans. Graph. 33, 4. Google ScholarDigital Library
    19. Kim, V., Li, W., Mitra, N., DiVerdi, S., and Funkhouser, T. 2012. Exploring collections of 3D models using fuzzy correspondences. ACM Trans. Graph. 31, 4. Google ScholarDigital Library
    20. Kolmogorov, V. 2006. Convergent tree-reweighted message passing for energy minimization. PAMI 28, 10. Google ScholarDigital Library
    21. Lim, J., Khosla, A., and Torralba, A. 2014. FPM: fine pose parts-based model with 3D CAD models. In ECCV.Google Scholar
    22. Liu, C., Yuen, J., and Torralba, A. 2011. SIFT flow: Dense correspondence across scenes and its applications. PAMI 33, 5. Google ScholarDigital Library
    23. Sederberg, T. W., and Parry, S. R. 1986. Free-form deformation of solid geometric models. In SIGGRAPH. Google ScholarDigital Library
    24. Shen, C., Fu, H., Chen, K., and Hu, S. 2012. Structure recovery by part assembly. ACM Trans. Graph. 31, 6. Google ScholarDigital Library
    25. Shi, J., and Malik, J. 2000. Normalized cuts and image segmentation. PAMI 22, 8. Google ScholarDigital Library
    26. Snavely, N., Simon, I., Goesele, M., Szeliski, R., and Seitz, S. 2010. Scene reconstruction and visualization from community photo collections. Proceedings of the IEEE 98, 8.Google ScholarCross Ref
    27. Su, H., Huang, Q., Mitra, N., Li, Y., and Guibas, L. 2014. Estimating image depth using shape collections. ACM Trans. Graph. 33, 4. Google ScholarDigital Library
    28. Unnikrishnan, R., Pantofaru, C., and Hebert, M. 2007. Toward objective evaluation of image segmentation algorithms. PAMI 29, 6. Google ScholarDigital Library
    29. Wang, Y., Gong, M., Wang, T., Cohen-Or, D., Zhang, H., and Chen, B. 2013. Projective analysis for 3D shape segmentation. ACM Trans. Graph. 32, 6. Google ScholarDigital Library
    30. Xu, K., Zheng, H., Zhang, H., Cohen-Or, D., Liu, L., and Xiong, Y. 2011. Photo-inspired model-driven 3D object modeling. ACM Trans. Graph. 30, 4. Google ScholarDigital Library
    31. Zheng, Y., Chen, X., Cheng, M., Zhou, K., Hu, S., and Mitra, N. 2012. Interactive images: cuboid proxies for smart image manipulation. ACM Trans. Graph. 31, 4. Google ScholarDigital Library

ACM Digital Library Publication:


Overview Page: