Abstract
The frame-to-global-model approach is widely used for accurate 3D modeling from sequences of RGB-D images. Because still no perfect camera tracking system exists, the accumulation of small errors generated when registering and integrating successive RGB-D images causes deformations of the 3D model being built up. In particular, the deformations become significant when the scale of the scene to model is large. To tackle this problem, we propose a two-stage strategy to build in details a large-scale 3D model with minimal deformations where the first stage creates accurate small-scale 3D scenes in real-time from short subsequences of RGB-D images while the second stage re-organises all the results from the first stage in a geometrically consistent manner to reduce deformations as much as possible. By employing planar patches as the 3D scene representation, our proposed method runs in real-time to build accurate 3D models with minimal deformations even for large-scale scenes. Our experiments using real data confirm the effectiveness of our proposed method.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
3D Scene Dataset: http://www.stanford.edu/~qianyizh/projects/scenedata.html
RGB-D SLAM Dataset and Benchmark. http://vision.in.tum.de/data/datasets/rgbd-dataset
Blais, G., Levine, M.D.: Registering multi vie range data to create 3D computer objects. IEEE Trans. on PAMI 17(8), 820–824 (1995)
Cameral, R., Grisetti, G., Strasdat, H., Konolige, K., Burgard, W.: g2o: A general framework for graph optimisation. In: Proc. of ICRA (2011)
Chen, J., Bautembach, D., Izadi, S.: Scalable real-time volumetric surface reconstruction. ACM Transactions on Graphics 32(4), 113:1–113:16 (2013)
Henry, P., Fox, D., Bhowmik, A., Mongia, R.: Patch volumes: segmentation-based consistent mapping with RGB-D cameras. In: Proc. of 3DV 2013 (2013)
Henry, P., Krainin, M., Herbst, E., Ren, X., Fox, D.: RGB-D mapping: Using Kinect-style depth cameras for dense 3D modelling of indoor environments. International Journal of Robotics Research 31(5), 647–663 (2012)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. of ICCV, pp. 1150–1157 (1999)
Meilland, M., Comport, A.: On unifying key-frame and voxel-based dense visual SLAM at large scales. In: Proc. of IROS (2013)
Neibner, M., Zollhofer, M., Izadi, S., Stamminger, M.: Real-time 3D reconstruction at scale using voxel hashing. ACM Transactions on Graphics 32(6), 169:1–169:11 (2013)
Newcombe, R., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A., Kohli, P., Shotton, J., Hodges, S., Fitzgibbon, A.: Kinectfusion: real-time dense surface mapping and tracking. In: Proc. of ISMAR 2011, pp. 127–136 (2011)
Nguyen, C., Izadi, S., Lovell, D.: Modeling kinect sensor noise for improved 3D reconstruction and tracking. In: Proc. of 3DIM/PVT 2012, pp. 524–530 (2012)
Roth, H., Vona, M.: Moving volume kinectfusion. In: Proc. of BMVC (2012)
Segal, A., Haehnel, D., Thrun, S.: Generalized-ICP. Robotics: Science and Systems (2009)
Thomas, D., Sugimoto, A.: A flexible scene representation for 3D reconstruction using an RGB-D camera. In: Proc. of ICCV (2013)
Whelan, T., McDonald, J., Kaess, M., Fallon, M., Johansson, H., Leonard, J.: Kintinuous: Spatially extended kinectfusion. Advanced Reasoning with Depth Camera. In: Proc. of RSS Workshop on RGB-D (2012)
Zeng, M., Zhao, F., Zheng, J., Liu, X.: Octree-based fusion for realtime 3D reconstruction. Transaction of Graphical Models 75(3), 126–136 (2013)
Zhou, Q.-Y., Koltun, V.: Dense scene reconstruction with points of interest. ACM Transaction on Graphics 32(4), 112:1–112:8 (2013)
Zhou, Q.-Y., Miller, S., Koltun, V.: Elastic fragments for dense scene reconstruction. In: Proc. of ICCV (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Thomas, D., Sugimoto, A. (2015). A Two-Stage Strategy for Real-Time Dense 3D Reconstruction of Large-Scale Scenes. In: Agapito, L., Bronstein, M., Rother, C. (eds) Computer Vision - ECCV 2014 Workshops. ECCV 2014. Lecture Notes in Computer Science(), vol 8925. Springer, Cham. https://doi.org/10.1007/978-3-319-16178-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-319-16178-5_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16177-8
Online ISBN: 978-3-319-16178-5
eBook Packages: Computer ScienceComputer Science (R0)