Abstract
Surface reconstruction using patch-based multi-view stereo commonly assumes that the underlying surface is locally planar. This is typically not true so that least-squares fitting of a planar patch leads to systematic errors which are of particular importance for multi-scale surface reconstruction. In a recent paper [12], we determined the modulation transfer function of a classical patch-based stereo system. Our key insight was that the reconstructed surface is a box-filtered version of the original surface. Since the box filter is not a true low-pass filter this causes high-frequency artifacts. In this paper, we propose an extended reconstruction model by weighting the least-squares fit of the 3D patch. We show that if the weighting function meets specified criteria the reconstructed surface is the convolution of the original surface with that weighting function. A choice of particular interest is the Gaussian which is commonly used in image and signal processing but left unexploited by many multi-view stereo algorithms. Finally, we demonstrate the effects of our theoretic findings using experiments on synthetic and real-world data sets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bellocchio, F., Borghese, N.A., Ferrari, S., Piuri, V.: 3D Surface Reconstruction: Multi-Scale Hierarchical Approaches. Springer, New York (2013)
Fuhrmann, S., Goesele, M.: Fusion of depth maps with multiple scales. In: SIGGRAPH Asia (2011)
Furukawa, Y., Curless, B., Seitz, S.M., Szeliski, R.: Towards internet-scale multi-view stereo. In: CVPR (2010)
Gargallo, P., Sturm, P.: Bayesian 3D modeling from images using multiple depth maps. In: CVPR (2005)
Goesele, M., Snavely, N., Curless, B., Hoppe, H., Seitz, S.M.: Multi-view stereo for community photo collections. In: ICCV (2007)
Goldlücke, B., Cremers, D.: A superresolution framework for high-accuracy multiview reconstruction. In: Denzler, J., Notni, G., Süße, H. (eds.) DAGM 2009. LNCS, vol. 5748, pp. 342–351. Springer, Heidelberg (2009)
Gruen, A., Baltsavias, E.P.: Geometrically constrained multiphoto matching. Photogrammetric Engineering & Remote Sensing 54(5), 633–641 (1988)
Habbecke, M., Kobbelt, L.: A surface-growing approach to multi-view stereo reconstruction. In: CVPR (2007)
Hosni, A., Bleyer, M., Gelautz, M., Rhemann, C.: Local stereo matching using geodesic support weights. In: ICIP (2009)
Hu, X., Mordohai, P.: A quantitative evaluation of confidence measures for stereo vision. PAMI 34(11), 2121–2133 (2012)
Kanade, T., Okutomi, M.: A stereo matching algorithm with an adaptive window: Theory and experiment. PAMI 16(9), 920–932 (1994)
Klowsky, R., Kuijper, A., Goesele, M.: Modulation transfer function of patch-based stereo systems. In: CVPR (2012)
Micusik, B., Kosecka, J.: Multi-view superpixel stereo in man-made environments. Tech. rep., Dept. Computer Science, George Mason University (2008)
Middlebury multi-view stereo evaluation, http://vision.middlebury.edu/mview/
Mücke, P., Klowsky, R., Goesele, M.: Surface reconstruction from multi-resolution sample points. In: VMV (2011)
Physically based rendering, http://www.pbrt.org
Pickup, L., Capel, D., Roberts, S., Zisserman, A.: Bayesian methods for image super-resolution. The Computer Journal 52(1), 101–113 (2007)
Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: CVPR (2006)
Snavely, N., Seitz, S.M., Szeliski, R.: Skeletal sets for efficient structure from motion. In: CVPR (2008)
Yang, Q., Yang, R., Davis, J., Nister, D.: Spatial-depth super resolution for range images. In: CVPR (2007)
Yoon, K.J., Kweon, I.S.: Locally adaptive support-weight approach for visual correspondence search. In: CVPR (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Klowsky, R., Kuijper, A., Goesele, M. (2013). Weighted Patch-Based Reconstruction: Linking (Multi-view) Stereo to Scale Space. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2013. Lecture Notes in Computer Science, vol 7893. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38267-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-38267-3_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38266-6
Online ISBN: 978-3-642-38267-3
eBook Packages: Computer ScienceComputer Science (R0)