Skip to main content
SpringerLink
Log in

Global, Dense Multiscale Reconstruction for a Billion Points

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

We present a variational approach for surface reconstruction from a set of oriented points with scale information. We focus particularly on scenarios with nonuniform point densities due to images taken from different distances. In contrast to previous methods, we integrate the scale information in the objective and globally optimize the signed distance function of the surface on a balanced octree grid. We use a finite element discretization on the dual structure of the octree minimizing the number of variables. The tetrahedral mesh is generated efficiently with a lookup table which allows to map octree cells to the nodes of the finite elements. We optimize memory efficiency by data aggregation, such that robust data terms can be used even on very large scenes. The surface normals are explicitly optimized and used for surface extraction to improve the reconstruction at edges and corners.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Notes

  1. We used CMPMVS 0.6.0 with the largeScale option.

  2. http://lmb.informatik.uni-freiburg.de/people/ummenhof/multiscalefusion.

References

  • Bailer, C., Finckh, M., & Lensch, H. P. A. (2012). Scale robust multi view stereo. In A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, & C. Schmid (Eds.), Computer vision ECCV 2012 (Vol. 7574, pp. 398–411)., Lecture Notes in Computer Science Berlin: Springer.

    Chapter  Google Scholar 

  • Blacker, T. D., & Meyers, R. J. (1993). Seams and wedges in plastering: A 3-D hexahedral mesh generation algorithm. Engineering with Computers, 9(2), 83–93. doi:10.1007/BF01199047.

    Article  Google Scholar 

  • Bolitho, M., Kazhdan, M., Burns, R., & Hoppe, H. (2007). Multilevel streaming for out-of-core surface reconstruction. In Proceedings of the fifth eurographics symposium on geometry processing, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, SGP ’07, pp 69–78.

  • Calakli, F., & Taubin, G. (2011). SSD: Smooth signed distance surface reconstruction. Computer Graphics Forum, 30(7), 1993–2002. doi:10.1111/j.1467-8659.2011.02058.x.

    Article  Google Scholar 

  • Curless, B., & Levoy, M. (1996). A volumetric method for building complex models from range images. In Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, ACM, New York, NY, USA, SIGGRAPH ’96, pp 303–312. doi:10.1145/237170.237269.

  • Estellers, V., Scott, M., Tew, K., & Soatto, S. (2015). Robust poisson surface reconstruction. In J. F. Aujol, M. Nikolova, & N. Papadakis (Eds.), Proceedings of the 5th International Conference on Scale Space and Variational Methods in Computer Vision, SSVM, Lège-Cap Ferret, France, 31 May–4 June 2015 (Vol. 9087, pp. 525–537). Cham: Springer International Publishing. doi:10.1007/978-3-319-18461-6_42.

  • Frahm, J. M., Fite-Georgel, P., Gallup, D., Johnson, T., Raguram, R., Wu, C., et al. (2010). Building Rome on a cloudless day. In K. Daniilidis, P. Maragos, & N. Paragios (Eds.), Computer vision ECCV 2010 (Vol. 6314, pp. 368–381)., Lecture Notes in Computer Science Berlin: Springer.

    Chapter  Google Scholar 

  • Fuhrmann, S., & Goesele, M. (2011). Fusion of depth maps with multiple scales. In Proceedings of the 2011 SIGGRAPH Asia conference, ACM, New York, NY, USA, SA ’11, (pp. 148:1–148:8). doi:10.1145/2024156.2024182.

  • Fuhrmann, S., & Goesele, M. (2014). Floating scale surface reconstruction. ACM Transactions on Graphics, 33(4), 46:1–46:11. doi:10.1145/2601097.2601163.

    Article  Google Scholar 

  • Fuhrmann, S., Langguth, F., & Goesele, M. (2014). MVE—A multi-view reconstruction environment. In Proceedings of the eurographics workshop on graphics and cultural heritage (GCH).

  • Gargantini, I. (1982). Linear octtrees for fast processing of three-dimensional objects. Computer Graphics and Image Processing, 20(4), 365–374. doi:10.1016/0146-664X(82)90058-2.

    Article  Google Scholar 

  • Goesele, M., Snavely, N., Curless, B., Hoppe, H., & Seitz, S. (2007). Multi-view stereo for community photo cCollections. In IEEE 11th international conference on computer vision, 2007. ICCV 2007, pp. 1–8. doi:10.1109/ICCV.2007.4408933.

  • Hiep V.H., Keriven, R., Labatut, P., & Pons, J.P. (2009). Towards high-resolution large-scale multi-view stereo. In IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009, pp 1430–1437. doi:10.1109/CVPR.2009.5206617.

  • Hirschmüller, H. (2005). Accurate and efficient stereo processing by semi-global matching and mutual information. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol. 2, pp. 807–814 vol. 2. doi:10.1109/CVPR.2005.56.

  • Jancosek, M., & Pajdla, T. (2011). Multi-view reconstruction preserving weakly-supported surfaces. In 2011 IEEE conference on computer vision and pattern recognition (CVPR), pp. 3121–3128. doi:10.1109/CVPR.2011.5995693.

  • Ju, T., Losasso, F., Schaefer, S., & Warren, J. (2002). Dual Contouring of Hermite Data. In Proceedings of the 29th annual conference on computer graphics and interactive techniques, ACM, New York, NY, USA, SIGGRAPH ’02, pp 339–346. doi:10.1145/566570.566586.

  • Kazhdan, M., & Hoppe, H. (2013). Screened Poisson surface reconstruction. ACM Transactions on Graphics, 32(3), 29:1–29:13. doi:10.1145/2487228.2487237.

    Article  MATH  Google Scholar 

  • Kazhdan, M., Klein, A., Dalal, K., & Hoppe, H. (2007). Unconstrained isosurface extraction on arbitrary octrees. In Proceedings of the fifth eurographics symposium on geometry processing, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, SGP ’07 (pp. 125–133).

  • Kobbelt, L.P., Botsch, M., Schwanecke, U., & Seidel, H.P. (2001). Feature sensitive surface extraction from volume data. In Proceedings of the 28th annual conference on computer graphics and interactive techniques, ACM, New York, NY, USA, SIGGRAPH ’01 (pp. 57–66). doi:10.1145/383259.383265.

  • Labatut, P., Pons, J. P., & Keriven, R. (2009). Robust and efficient surface reconstruction from Range data. Computer Graphics Forum, 28(8), 2275–2290. doi:10.1111/j.1467-8659.2009.01530.x.

    Article  Google Scholar 

  • Lewiner, T., Mello, V., Peixoto, A., Pesco, S., & Lopes, H. (2010). Fast generation of pointerless octree duals. Computer Graphics Forum, 29(5), 1661–1669. doi:10.1111/j.1467-8659.2010.01775.x.

    Article  Google Scholar 

  • Li, X., Andersen, D.G., Kaminsky, M., & Freedman, M.J. (2014). Algorithmic improvements for fast concurrent Cuckoo hashing. In Proceedings of the ninth European conference on computer systems, ACM, New York, NY, USA, EuroSys ’14 (pp. 27:1–27:14). doi:10.1145/2592798.2592820.

  • Manson, J., Petrova, G., & Schaefer, S. (2008). Streaming surface reconstructionUsing wavelets. In Proceedings of the symposium on geometry processing, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, SGP ’08. (pp. 1411–1420).

  • Marchal, L. (2009). Advances in octree-based all-hexahedral meshgeneration: Handling sharp features. In B. W. Clark (Ed.), Proceedings of the 18th international seshing roundtable (pp. 65–84). Berlin Heidelberg: Springer.

  • Mavriplis, D. J. (1995). An advancing front Delaunay triangulation algorithm designed for robustness. Journal of Computational Physics, 117(1), 90–101. doi:10.1006/jcph.1995.1047.

    Article  MATH  MathSciNet  Google Scholar 

  • Müller, M., Charypar, D., & Gross, M. (2003). Particle-based fluid simulation for interactive applications. In Proceedings of the 2003 ACM SIGGRAPH/eurographics symposium on computer animation, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, SCA ’03 (pp. 154–159).

  • Pock, T., Zebedin, L., & Bischof, H. (2011). TGV-Fusion. In C. S. Calude, G. Rozenberg, & A. Salomaa (Eds.), Rainbow of computer science (Vol. 6570, pp. 245–258)., Lecture Notes in Computer Science Berlin: Springer.

    Chapter  Google Scholar 

  • Ruppert, J., & Seidel, R. (1992). On the difficulty of triangulating three-dimensional nonconvex polyhedra. Discrete & Computational Geometry, 7(1), 227–253. doi:10.1007/BF02187840.

    Article  MATH  MathSciNet  Google Scholar 

  • Sagawa, R., Nishino, K., & Ikeuchi, K. (2005). Adaptively merging large-scale range data with reflectance properties. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(3), 392–405. doi:10.1109/TPAMI.2005.46.

    Article  Google Scholar 

  • Schaefer, S., & Warren, J. (2004). Dual marching cubes: Primal contouring of dual grids. In 12th Pacific conference on computer graphics and applications, 2004. PG 2004. Proceedings, pp 70–76. doi:10.1109/PCCGA.2004.1348336.

  • Seitz, S., Curless, B., Diebel, J., Scharstein, D., & Szeliski, R. (2006). A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms. In 2006 IEEE computer society conference on computer vision and pattern recognition, vol. 1, pp. 519–528. doi:10.1109/CVPR.2006.19.

  • Shewchuk, J.R. (1998). Tetrahedral mesh generation by Delaunay refinement. In Proceedings of the fourteenth annual symposium on computational geometry, ACM, New York, NY, USA, SCG ’98, pp. 86–95. doi:10.1145/276884.276894.

  • Ummenhofer, B., & Brox, T. (2015). Global, dense multiscale reconstruction for a billion points. In IEEE international conference on computer vision (ICCV).

  • Wilson, K., & Snavely, N. (2014). Robust global translations with 1dsfm. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Eds.), Computer vision ECCV 2014 (Vol. 8691, pp. 61–75)., Lecture Notes in Computer Science Berlin: Springer.

    Google Scholar 

  • Wu, C. (2013). Towards linear-time incremental structure from motion. In 2013 International conference on 3D vision—3DV 2013, pp. 127–134. doi:10.1109/3DV.2013.25.

  • Wu, C., Agarwal, S., Curless, B., & Seitz, S. (2011). Multicore bundle adjustment. In 2011 IEEE conference on computer vision and pattern recognition (CVPR), (pp. 3057–3064). doi:10.1109/CVPR.2011.5995552.

  • Zach, C. (2008). Fast and high quality fusion of depth maps. In Proceedings of the international symposium on 3D data processing, visualization and transmission (3DPVT), vol. 1.

Download references

Acknowledgements

We acknowledge funding by the ERC Starting Grant VideoLearn and the EU project Trimbot2020.

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Freiburg, 79110, Freiburg, Germany

    Benjamin Ummenhofer & Thomas Brox

Authors
  1. Benjamin Ummenhofer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas Brox
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Benjamin Ummenhofer.

Additional information

Communicated by Rene Vidal, Katsushi Ikeuchi, Josef Sivic, and Christoph Schnoerr.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ummenhofer, B., Brox, T. Global, Dense Multiscale Reconstruction for a Billion Points. Int J Comput Vis 125, 82–94 (2017). https://doi.org/10.1007/s11263-017-1017-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-017-1017-7

Keywords

Search

Navigation