Abstract
This chapter describes what is possibly the earliest use of dense correspondence estimation for transferring semantic information between images of different scenes. The method described in this chapter was designed for non-parametric, “example-based” depth estimation of objects appearing in single photos. It consults a database of example 3D geometries and associated appearances, searching for those which look similar to the object in the photo. This is performed at the pixel level, in similar spirit to the more recent methods described in the following chapters. Those newer methods, however, use robust, generic dense correspondence estimation engines. By contrast, the method described here uses a hard-EM optimization to optimize a well-defined target function over the similarity of appearance/depth pairs in the database to appearance/estimated-depth pairs of a query photo. Results are presented demonstrating how depths associated with diverse reference objects may be assigned to different objects appearing in query photos. Going beyond visible shape, we show that the method can be employed for the surprising task of estimating shapes of occluded objects’ backsides. This, so long as the reference database contains examples of mappings from appearances to backside shapes. Finally, we show how the duality of appearance and shape may be exploited in order to “paint colors” on query shapes (“colorize” them) by simply reversing the matching from appearances to depths.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Assa, J., Wolf, L.: Diorama construction from a single image. In: Eurographics, pp. 599–608 (2007)
Atick, J., Griffin, P., Redlich, A.: Statistical approach to shape from shading: reconstruction of three-dimensional face surfaces from single two-dimensional images. Neural Comput. 8(6), 1321–1340 (1996)
Barron, J.T., Malik, J.: Shape, albedo, and illumination from a single image of an unknown object. In: Proceedings of Conference on Computer Vision Pattern Recognition, pp. 334–341. IEEE, Providence (2012)
Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of ACM SIGGRAPH Conference on Computer Graphics, pp. 187–194. ACM/Addison-Wesley, New York (1999)
Burt, P., Adelson, E.: The laplacian pyramid as a compact image code. IEEE Trans. Commun. 30, 532–540 (1983)
Chen, Y., Kim, T.K., Cipolla, R.: Inferring 3D shapes and deformations from single views. In: European Conference on Computer Vision, pp. 300–313. Springer, Heidelberg (2010)
Chen, X., Guo, Y., Zhou, B., Zhao, Q.: Deformable model for estimating clothed and naked human shapes from a single image. Vis. Comput. 29(11), 1187–1196 (2013)
Cipolla, R., Fletcher, G., Giblin, P.: Surface geometry from cusps of apparent contours. In: Proceedings of International Conference on Computer Vision, pp. 858–863 (1995)
Cole, F., Isola, P., Freeman, W.T., Durand, F., Adelson, E.H.: Shapecollage: occlusion-aware, example-based shape interpretation. In: European Conference on Computer Vision, pp. 665–678. Springer, Heidelberg (2012)
Criminisi, A., Reid, I., Zisserman, A.: Single view metrology. Int. J. Comput. Vis. 40(2), 123–148 (2000)
Cyberware: http://www.cyberware.com/
Delage, E., Lee, H., Ng, A.: Automatic single-image 3D reconstructions of indoor manhattan world scenes. In: Proceedings of the International Symposium of Robotics Research (ISRR), pp. 305–321 (2005)
Dovgard, R., Basri, R.: Statistical symmetric shape from shading for 3D structure recovery of faces. In: European Conference on Computer Vision, vol. 2, pp. 99–113. Springer, Berlin/Heidelberg (2004)
Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. arXiv preprint (2014) [arXiv:1411.4734]
Gupta, A., Satkin, S., Efros, A.A., Hebert, M.: From 3D scene geometry to human workspace. In: Proceedings of Conference on Computer Vision Pattern Recognition, pp. 1961–1968. IEEE, Providence (2011)
Han, J., Zhou, K., Wei, L., Gong, M., Bao, H., Zhang, X., Guo, B.: Fast example-based surface texture synthesis via discrete optimization. Vis. Comput. 22, 918–925 (2006)
Hassner, T.: Viewing real-world faces in 3D. In: Proceedings of International Conference on Computer Vision, pp. 3607–3614. IEEE, Sydney (2013). Available: www.openu.ac.il/home/hassner/projects/poses
Hassner, T., Basri, R.: Automatic depth-map colorization. In: Eurographics (short), pp. 73–76 (2006)
Hassner, T., Basri, R.: Example based 3D reconstruction from single 2D images. In: Beyond Patches Workshop at CVPR, p. 15 (2006)
Hassner, T., Basri, R.: Single view depth estimation from examples. arXiv preprint (2013) [arXiv:1304.3915]
Hassner, T., Zelnik-Manor, L., Leifman, G., Basri, R.: Minimal-cut model composition. In: International Conference on Shape Modeling and Applications (SMI’ 05), pp. 72–81 (2005)
Hassner, T., Mayzels, V., Zelnik-Manor, L.: On sifts and their scales. In: Proceedings of Conference on Computer Vision Pattern Recognition, pp. 1522–1528. IEEE, Providence (2012)
Hassner, T., Assif, L., Wolf, L.: When standard RANSAC is not enough: cross-media visual matching with hypothesis relevancy. Mach. Vis. Appl. 25(4), 971–983 (2014)
Hassner, T., Harel, S., Paz, E., Enbar, R.: Effective face frontalization in unconstrained images. In: Proceedings of Conference on Computer Vision Pattern Recognition (2015)
Hoiem, D., Efros, A., Hebert, M.: Automatic photo pop-up. ACM Trans. Graph. 24(3), 577–584 (2005)
Hoiem, D., Efros, A., Hebert, M.: Geometric context from a single image. In: Proceedings of International Conference on Computer Vision, pp. 654–661. IEEE Computer Society, Beijing (2005)
Horn, B.: Obtaining Shape from Shading Information. The Psychology of Computer Vision. McGraw-Hill, New York (1975)
Karsch, K., Liu, C., Kang, S.B.: Depth extraction from video using non-parametric sampling. In: European Conference on Computer Vision, pp. 775–788. Springer, Heidelberg (2012)
Kearns, M., Mansour, Y., Ng, A.: An information-theoretic analysis of hard and soft assignment methods for clustering. In: Proceedings of the NATO Advanced Study Institute on Learning in Graphical Models, pp. 495–520. Kluwer Academic, Norwell (1998)
Kemelmacher, I., Basri, R.: Molding face shapes by example. In: European Conference on Computer Vision, p. 2006 (277–288)
Kemelmacher-Shlizerman, I., Seitz, S.: Face reconstruction in the wild. In: Proceedings of International Conference on Computer Vision, pp. 1746–1753. IEEE, Washington (2011)
Kraevoy, V., Sheffer, A.: Cross-parameterization and compatible remeshing of 3D models. ACM Trans. Graph. 23(3), 861–869 (2004)
Leifman, G., Tal, A.: Mesh colorization. Comput. Graph. Forum 31(2), 421–430 (2012)
Liu, C., Yuen, J., Torralba, A., Sivic, J., Freeman, W.: Sift flow: dense correspondence across different scenes. In: European Conference on Computer Vision, pp. 28–42 (2008). Available: people.csail.mit.edu/celiu/ECCV2008/
Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011). Available: people.csail.mit.edu/celiu/SIFTflow/
Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. arXiv preprint (2015) [arXiv:1502.07411]
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Oswald, M.R., Toppe, E., Cremers, D.: Fast and globally optimal single view reconstruction of curved objects. In: Proceedings of Conference on Computer Vision Pattern Recognition, pp. 534–541. IEEE, Washington (2012)
Panagopoulos, A., Hadap, S., Samaras, D.: Reconstructing shape from dictionaries of shading primitives. In: Asian Conference on Computer Vision, pp. 80–94. Springer, Heidelberg (2013)
Praun, E., Sweldens, W., Schröder, P.: Consistent mesh parameterizations. In: Proceedings of ACM SIGGRAPH Conference on Computer Graphics, pp. 179–184. ACM, New York (2001)
Qiu, W., Wang, X., Bai, X., Yuille, A., Tu, Z.: Scale-space sift flow. In: Proceedings of Winter Conference on Applications of Computer Vision, pp. 1112–1119. IEEE, Steamboat Springs (2014)
Romdhani, S., Vetter, T.: Efficient, robust and accurate fitting of a 3D morphable model. In: Proceedings of International Conference on Computer Vision, p. 59 (2003)
Saxena, A., Sun, M., Ng, A.: Make3d: learning 3-D scene structure from a single still image. Trans. Pattern Anal. Mach. Intell. 31(5), 824–840 (2009)
Schwing, A.G., Urtasun, R.: Efficient exact inference for 3D indoor scene understanding. In: European Conference on Computer Vision, pp. 299–313. Springer, Heidelberg (2012)
Tau, M., Hassner, T.: Dense correspondences across scenes and scales. IEEE Trans. Pattern Anal. Mach. Intell. PP(99), 1 (2015)
Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Gool, L.: Shape-from-recognition: recognition enables meta-data transfer. Comput. Vis. Image Underst. 113(12), 1222–1234 (2009)
Toucan virtual museum. Available: http://www.toucan.co.jp/indexE.html
Turk, G.: Texture synthesis on surfaces. In: Proceedings of ACM SIGGRAPH Conference on Computer Graphics, pp. 347–354. ACM, New York (2001)
USF: DARPA Human-ID 3D Face Database: Courtesy of Prof. Sudeep Sarkar. University of South Florida, Tampa. http://marthon.csee.usf.edu/HumanID/
Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms. In: Proceedings of International Conference on Multimedia, pp. 1469–1472 (2010). Available: www.vlfeat.org/
Wei, L.Y., Levoy, M.: Fast texture synthesis using tree-structured vector quantization. In: Proceedings of ACM SIGGRAPH Conference on Computer Graphics, pp. 479–488. ACM/Addison-Wesley, New York (2000)
Wei, L.Y., Levoy, M.: Texture synthesis over arbitrary manifold surfaces. In: Proceedings of ACM SIGGRAPH Conference on Computer Graphics, pp. 355–360. ACM, New York (2001)
Witkin, A.: Recovering surface shape and orientation from texture. Artif. Intell. 17(1–3), 17–45 (1981)
Xiong, Y., Chakrabarti, A., Basri, R., Gortler, S.J., Jacobs, D.W., Zickler, T.: From shading to local shape. arXiv preprint (2014) [arXiv:1310.2916]
Ying, L., Hertzmann, A., Biermann, H., Zorin, D.: Texture and shape synthesis on surfaces. In: Proceedings of the 12th Eurographics Workshop on Rendering Techniques, pp. 301–312. Springer, Heidelberg (2001)
Zhou, K., Wang, X., Tong, Y., Desbrun, M., Guo, B., Shum, H.Y.: Texturemontage: seamless texturing of arbitrary surfaces from multiple images. ACM Trans. Graph. 24(3), 1148–1155 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Hassner, T., Basri, R. (2016). From Images to Depths and Back. In: Hassner, T., Liu, C. (eds) Dense Image Correspondences for Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-319-23048-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-23048-1_8
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23047-4
Online ISBN: 978-3-319-23048-1
eBook Packages: EngineeringEngineering (R0)