Abstract
This paper proposes an efficient multi-view 3D reconstruction method based on randomization and propagation scheme. Our method progressively refines a 3D model of a given scene by randomly perturbing the initial guess of 3D points and propagating photo-consistent ones to their neighbors. While finding local optima is an ordinary method for better photo-consistency, our randomization and propagation takes lucky matchings to spread better points replacing old ones for reducing the computational complexity. Experiments show favorable efficiency of the proposed method accompanied by competitive accuracy with the state-of-the-art methods.
Similar content being viewed by others
References
Agarwal S, Snavely N, Simon I, Seitz SM, Szeliski R (2009) Building rome in a day. In: Proc. of Intl Conf. on Computer Vision (ICCV), pages 72-79. IEEE
Barnes C, Shechtman E, Finkelstein A, Goldman DB (2009) Patchmatch: A randomized correspondence algorithm for structural image editing. ACM Trans Graph 28(3):24
Besse F, Rother C, Fitzgibbon AW, Kautz J (2012) Pmbp: Patchmatch belief propagation for correspondence field estimation. In: Proc. of British Machine Vision Conf. (BMVC)
Bleyer M, Rhemann C, Rother C (2011) Patchmatch stereo - stereo matching with slanted support windows. In: Proc. of British Machine Vision Conf. (BMVC)
Bradley D, Boubekeur T, Heidrich W (2008) Accurate multi-view reconstruction using robust binocular stereo and surface meshing. In Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR):1–8
Campbell ND, Vogiatzis G, Hernandez C, Cipolla R (2008). In: Proc. of European Conf. on Computer Vision (ECCV), pages 766–779
Chang JY, Park H, Park IK, Lee KM, Lee SU (2011) Gpu-friendly multi-view stereo reconstruction using surfel representation and graph cuts. Comput Vis Image Underst 115(5):620–634
Cui P, Liu Y, Wu P, Li J, Yi S (2015) An effective multiview stereo method for uncalibrated images. In: Proc. of Chinese Conference on Computer Vision, pp 124–133
Deng Y, Liu Y, Dai Q, Zhang Z, Wang Y (2012) Noisy depth maps fusion for multiview stereo via matrix completion. IEEE J Sel Top Sign Proces 6(5):566–582
Frahm J-M, Fite-Georgel P, Gallup D, Johnson T, Raguram R, Wu C, Jen Y-H, Dunn E, Clipp B, Lazebnik S, Pollefeys M (2010) Building rome on a cloudless day. In: Proc. of European Conf. on Computer Vision (ECCV), pages 368–381
Furukawa Y, Curless B, Seitz SM, Szeliski R (2010) Towards internet-scale multi-view stereo. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp 1434–1441
Furukawa Y, Ponce J (2010) Accurate, dense, and robust multiview stereopsis. IEEE Trans Pattern Anal Mach Intell 32(8):1362–1376
Goesele M, Curless B, Seitz SM (2006) Multi-view stereo revisited. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), vol 2, pp 2402–2409
Goesele M, Snavely N, Curless B, Hoppe H, Seitz SM (2007) Multi-view stereo for community photo collections. In: Proc. of Intl Conf. on Computer Vision (ICCV)
Heise P, Klose S, Jensen B, Knoll A (2013) Pm-huber: Patchmatch with huber regularization for stereo matching. In: Proc. of Intl Conf. on Computer Vision (ICCV)
Hiep VH, Keriven R, Labatut P, Pons J-P (2009) Towards high-resolution large-scale multi-view stereo. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp 1430–1437
Jancosek M, Pajdla T (2009) Segmentation based multi-view stereo Computer VisionWinterWorkshop
Jancosek M, Pajdla T (2014) Exploiting visibility information in surface reconstruction to preserve weakly supported surfaces. International Scholarly Research Notices:2014
Jancosek M, Shekhovtsov A, Pajdla T (2009) Scalable multi-view stereo.. In: Computer Vision Workshops, (ICCV Workshops) IEEE 12Th International Conference on IEEE, pp 1526–1533
Kazhdan M, Bolitho M, Hoppe H (2006) Poisson surface reconstruction. In: Proc. of Sympdium on Geometry Processing
Kolev K, Pock T, Cremers D (2010) Anisotropic minimal surfaces integrating photoconsistency and normal information for multiview stereo. In: Proc. of European Conf. on Computer Vision (ECCV), pages 538-551. Springer
Kostrikov I, Horbert E, Leibe B (2014) Probabilistic labeling cost for high-accuracy multi-view reconstruction. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). IEEE
Li J, Li E, Chen Y, Xu L, Zhang Y (2010) Bundled depth-map merging for multi-view stereo. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp 2769–2776
Merrell P, Akbarzadeh A, Wang L, Mordohai P, Frahm J-M, Yang R, Nister D, Pollefeys M (2007) Real-time visibility-based fusion of depth maps. In: Proc. of Intl Conf. on Computer Vision (ICCV)
Newcombe RA, Davison AJ (2010) Live dense reconstruction with a single moving camera. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages 1498-1505. IEEE
Oliva A, Torralba A (2001) Modeling the shape of the scene A holistic representation of the spatial envelope. Int J Comput Vis 42(3):145–175
Pons J-P, Keriven R, Faugeras O (2005) Modelling dynamic scenes by registering multi-view image sequences. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), vol 2, pp 822–827
Rong G, Tan T-S (2006) Jump flooding in gpu with applications to voronoi diagram and distance transform. In: Proc. of Symposium on Interactive 3D Graphics and Games, pp 109–116
Scharstein D, Szeliski R (2002) A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int J Comput Vis 47:742
Schning J, Gunther H (2015) Evaluation of multi-view 3D reconstruction software Computer Analysis of Images and Patterns Springer International Publishing
Schroers C, Zimmer H, Valgaerts L, Bruhn A, Demetz O, Weickert J (2012) Anisotropic range image integration. Springer, Berlin Heidelberg
Seitz SM, Curless B, Diebel J, Scharstein D, Szeliski R (2006) A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp 519–528
Shen S (2013) Accurate multiple view 3d reconstruction using patch-based stereo for large-scale scenes. IEEE Trans Image Process 22(5):1901–1914
Snavely N, Seitz SM, Szeliski R (2008) Modeling the world from internet photo collections. Int J Comput Vis 80(2):189–210
Strecha C, Fransens R, Van Gool L (2004) Wide-baseline stereo from multiple views: a probabilistic account. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) pages I-552
Strecha C, Fransens R, Van Gool L (2006) Combined depth and outlier estimation in multi-view stereo. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR):2394–2401
Strecha C, von Hansen W, Van Gool L, Fua P, Thoennessen U (2008) On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Sẗuhmer J, Gumhold S, Cremers D (2010) Real-time dense geometry from a handheld camera. In: Pattern Recognition, pages 11-20. Springer
Tanskanen P, Kolev K, Meier L, Camposeco F, Saurer O, Pollefeys M (2013) Live metric 3d reconstruction on mobile phones. In: Proc. of Intl Conf. on Computer Vision (ICCV). IEEE
Tola E, Strecha C, Fua P (2012) Efficient large scale multi-view stereo for ultra high resolution image sets. Mach Vis Appl 23(5):903–920
Tylecek R (2009) Depth map fusion with camera position refinement. In: Computer Vision Winter Workshop
Tylecek R, Sara R (2010) Refinement of surface mesh for accurate multiview reconstruction. The International Journal of Virtual Reality 9(1):45–54
Uh Y, Matsushita Y, Byun H (2014) ”Efficient multiview stereo by random-search and propagation.” 3D Vision (3DV), 2014 2nd International Conference on. Vol. 1 IEEE
Wu C (2013) Towards Linear-time Incremental Structure From Motion. In: Proc. of Int’l Conf. on 3D Vision, IEEE
Zaharescu A, Boyer E, Horaud R (2007) Transformesh: a topology-adaptive mesh-based approach to surface evolution. In: Proc. of Asian Conf. on Computer Vision (ACCV), pp 166–175
Zaharescu A, Cagniart C, Ilic S, Boyer E, Horaud R (2008) Camera-clustering for multi-resolution 3-d surface reconstruction. In: Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications-M2SFA2
Acknowledgments
This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIP) (No.B0101-16-0307, Basic Software Research in Human-level Lifelong Machine Learning (Machine Learning Center))
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Uh, Y., Byun, H. Multi-view 3D reconstruction by random-search and propagation with view-dependent patch maps. Multimed Tools Appl 75, 16597–16614 (2016). https://doi.org/10.1007/s11042-016-3621-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3621-x