iccv iccv2013 iccv2013-250 iccv2013-250-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Srikumar Ramalingam, Matthew Brand
Abstract: We propose a novel and an efficient method for reconstructing the 3D arrangement of lines extracted from a single image, using vanishing points, orthogonal structure, and an optimization procedure that considers all plausible connectivity constraints between lines. Line detection identifies a large number of salient lines that intersect or nearly intersect in an image, but relatively a few of these apparent junctions correspond to real intersections in the 3D scene. We use linear programming (LP) to identify a minimal set of least-violated connectivity constraints that are sufficient to unambiguously reconstruct the 3D lines. In contrast to prior solutions that primarily focused on well-behaved synthetic line drawings with severely restricting assumptions, we develop an algorithm that can work on real images. The algorithm produces line reconstruction by identifying 95% correct connectivity constraints in York Urban database, with a total computation time of 1 second per image.
[1] M. B. Clowes. On seeing things. AI, 1971.
[2] F. Cole, P. Isola, W. T. Freeman, F. Durand, and E. H. Adelson. Shapecollage: Occlusion-aware, example-based shape interpretation. In ECCV, 2012.
[3] J. Coughlan and A. Yuille. Manhattan world: Compass direction from a single image by bayesian inference. In ICCV, 1999.
[4] A. Criminisi, I. Reid, and A. Zisserman. Single view metrology. IJCV, 2000.
[5] E. Delage, H. Lee, and A. Ng. Automatic single-image 3d reconstructions of indoor manhattan world scenes. In ISRR, 2005.
[6] P. Denis, J. Elder, and F. Estrada. Efficient edge-based methods for estimating manhattan frames in urban imagery. In ECCV, 2008.
[7] A. Flint, D. Murray, and I. Reid. Manhatten scene understanding using monocular, stereo, and 3D features. In ICCV, 2011.
[8] D. Fouhey, V. Delaitre, A. Gupta, A. Efros, I. Laptev, and J. Sivic. People watching: Human actions as a cue for single view geometry. In ECCV, 2012.
[9] A. Gupta, A. A. Efros, and M. Hebert. Blocks world revisited: Image understanding using qualitative geometry and mechanics. In ECCV, 2010.
[10] F. Han and S.-C. Zhu. Bottom-up/top-down image parsing with attribute grammar. PAMI, 2009.
[11] V. Hedau, D. Hoiem, and D. Forsyth. Recovering the spatial layout of cluttered rooms. In ICCV, 2009.
[12] D. Hoiem, A. A. Efros, and M. Hebert. Automatic photo pop-up. ACM Trans. Graph., 2005.
[13] D. Hoiem, A. A. Efros, and M. Hebert. Recovering surface layout from an image. IJCV, 2007.
[14] D. A. Huffman. Impossible objects as nonsense sentences. Machine Intelligence, 1971 .
[15] A. Jain, C. Kurz, T. Thormahlen, and H. Seidel. Exploiting global connectivity constraints for reconstruction of 3d line segment from images. In CVPR, 2010.
[16] T. Kanade. A theory of origami world. AI, 1980.
[17] J. Kosecha and W. Zhang. Video compass. In ECCV, 2002.
[18] D. Lee, A. Gupta, M. Hebert, and T. Kanade. Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In NIPS, 2010.
[19] D. Lee, M. Hebert, and T. Kanade. Geometric reasoning for single image structure recovery. In CVPR, 2009.
[20] J. Malik. Interpreting line drawings of curved objects. IJCV, 1987.
[21] B. Micusik, H. Wildenauer, and J. Kosecka. Detection and matching of rectilinear structures. In CVPR, 2008.
[22] S. Ramalingam, J. Pillai, A. Jain, and Y. Taguchi. Manhattan junction catalogue for spatial reasoning of indoor scenes. In CVPR, 2013.
[23] L. Roberts. Machine perception of three-dimensional solids. PhD thesis, MIT, 1963.
[24] A. Saxena, S. H. Chung, and A. Y. Ng. 3-D depth reconstruction from a single still image. IJCV, 2008.
[25] A. G. Schwing, T. Hazan, M. Pollefeys, and R. Urtasun. Ef-
[26]
[27]
[28]
[29]
[30] [3 1]
[32] ficient structured prediction for 3D indoor scene understanding. In CVPR, 2012. P. Sturm and S. Maybank. A method for interactive 3d reconstruction of piecewise planar objects from single images. In BMVC, 1999. K. Sugihara. Machine Interpretation of Line Drawings. MIT Press, 1986. C. Vanegas, D. Aliaga, and D. Benes. Building reconstruction using manhattan-world grammars. In CVPR, 2010. P. Varley. Automatic Creation of Boundary-Representation Models from Single Line Drawings. PhD thesis, Cardiff University, 2003. D. Waltz. Generating semantic descriptions from line drawings of scenes with shadows. Technical Report, MIT, 1972. W. Whiteley. A matroid on hypergraphs, with applications in scene analysis and geometry. Discrete and Computational Geometry, 1989. S. Yu, H. Zhang, and J. Malik. Inferring spatial layout from a single image via depth-ordered grouping. In Proc. Workshop on Perceptual Organization in Computer Vision, 2008. 504