Parallel Large-Scale Structure from Motion by Distributed Averaging
Pages 565 - 572
Abstract
With the development of computer vision, Structure from Motion (SFM) which recovers sparse point clouds from image sequences has achieved great success. Large-scale scenes cannot be reconstructed with a single compute node so that we introduce a divide-and-conquer framework to solve the distributed SFM problem. First, we attach great importance to the efficiency of image matching and geometric filtering, which takes up a lot of time in the traditional SFM problem. We use the GPS information of images to calculate the GPS neighborhood. The number of image matches is greatly reduced by matching each image with only valid GPS neighbors, and a robust matching relationship is obtained. Second, the calculated matching relationship is used as the initial camera graph to be divided into multiple subgraphs by the clustering algorithm, and local SFM is executed on several computing nodes to register the local cameras. Finally, all local camera poses are integrated and optimized to complete the global camera registration. Our system can solve the structure from motion problem in large-scale scenes with accuracy and efficiency.
References
[1]
S. Agarwal, Y. Furukawa, N. Snavely, I. Simon, B. Curless, S. M. Seitz, and R. Szeliski. Building rome in a day. Commun. ACM, 54(10):105--112, 2011.
[2]
M. Arie-Nachimson, S. Z. Kovalsky, I. KemelmacherShlizerman, A. Singer, and R. Basri. Global motion estimation from point matches. In 3DIMPVT, 2012.
[3]
B. Bhowmick, S. Patra, A. Chatterjee, V. M. Govindu, S. Banerjee, B. Bhowmick, S. Patra, A. Chatterjee, V. M. Govindu, and S. Banerjee. Divide and conquer: Efficient large-scale structure from motion using graph partitioning. 2014.
[4]
M. Brand, M. Antone, and S. Teller. Spectral solution of large-scale extrinsic camera calibration as a graph embedding problem. In ECCV, 2004.
[5]
L. Carlone, R. Tron, K. Daniilidis, and F. Dellaert. Initialization techniques for 3d slam: a survey on rotation estimation and its use in pose graph optimization. In ICRA, 2015.
[6]
M. Farenzena, A. Fusiello, and R. Gherardi. Structure and motion pipeline on a hierarchical cluster tree. In ICCV Workshops, 2009.
[7]
A. Chatterjee and V. M. Govindu. Efficient and robust largescale rotation averaging. In ICCV, 2013.
[8]
M. Havlena, A. Torii, and T. Pajdla. Efficient structure from motion by graph optimization. In ECCV, 2010.
[9]
Z. Cui, N. Jiang, C. Tang, and P. Tan. Linear global translation estimation with feature tracks. In BMVC, 2015.
[10]
Z. Cui and P. Tan. Global structure-from-motion by similarity averaging. In ICCV, 2015.
[11]
I. S. Dhillon, Y. Guan, and B. Kulis. Weighted graph cuts without eigenvectors a multilevel approach. PAMI, 29(11):1944--1957, 2007.
[12]
M. Lhuillier and L. Quan. A quasi-dense approach to surface reconstruction from uncalibrated images. PAMI, 27(3):418-- 433, 2005.
[13]
A. Eriksson, J. Bastian, T.-J. Chin, and M. Isaksson. A consensus-based framework for distributed bundle adjustment. In CVPR, 2016.
[14]
J.-M. Frahm, P. Fite-Georgel, D. Gallup, T. Johnson, R. Raguram, C. Wu, Y.-H. Jen, E. Dunn, B. Clipp, S. Lazebnik, and M. Pollefeys. Building rome on a cloudless day. In ECCV, 2010.
[15]
B. Resch, H. P. Lensch, O. Wang, M. Pollefeys, and A. S. Hornung. Scalable structure from motion for densely sampled videos. In CVPR, 2015.
[16]
V. M. Govindu. Combining two-view constraints for motion estimation. In CVPR, 2001.
[17]
V. M. Govindu. Lie-algebraic averaging for globally consistent motion estimation. In CVPR, 2004.
[18]
S. Haner and A. Heyden. Covariance propagation and next best view planning for 3d reconstruction. In SSBA, 2012.
[19]
R. I. Hartley, J. Trumpf, Y. Dai, and H. Li. Rotation averaging. IJCV, 103(3):267--305, 2013.
[20]
N. Jiang, Z. Cui, and P. Tan. A global linear method for camera pose registration. In ICCV, 2013.
[21]
N. Jiang, P. Tan, and L. F. Cheong. Seeing double without confusion: Structure-from-motion in highly ambiguous scenes. In ICCV, 2012.
[22]
R. Toldo, R. Gherardi, M. Farenzena, and A. Fusiello. Hierarchical structure-and-motion recovery from uncalibrated images. CoRR, abs/1506.00395, 2015.
[23]
L. Kneip, D. Scaramuzza, and R. Siegwart. A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation. In CVPR, 2011.
[24]
J. Heinly, J. L. Schonberger, E. Dunn, and J. M. Frahm. Reconstructing the world in six days. In CVPR, 2015.
[25]
D. Martinec and T. Pajdla. Robust rotation and translation estimation in multiview reconstruction. In ICPR, 2007.
[26]
P. Moulon, P. Monasse, and R. Marlet. Global fusion of relative motions for robust, accurate and scalable structure from motion. In ICCV, 2013.
[27]
K. Ni, D. Steedly, and F. Dellaert. Out-of-corebundle adjustmentforlarge-scale3d reconstruction. In ICCV, 2007.
[28]
D. Nister. An efficient solution to the five-point relative pose problem. PAMI, pages 756--770, 2004.
[29]
Shi, J., Malik, J., 2000. Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 888--905.
[30]
X. Li, C. Wu, C. Zach, S. Lazebnik, and J.-M. Frahm. Modeling and recognition of landmark image collections using iconic scene graphs. In ECCV, 2008.
[31]
L. Zhou, S. Zhu, T. Shen, J. Wang, T. Fang, and L. Quan. Progressive large scale-invariant image matching in scale space. In ICCV, 2017.
[32]
M. Arie-Nachimson, S. Z. Kovalsky, I. KemelmacherShlizerman, A. Singer, and R. Basri. Global motion estimation from point matches. In 3DIMPVT, 2012.
[33]
O. Ozyesil and A. Singer. Robust camera location estimation by convex programming. In CVPR, 2015.
[34]
M. Pollefeys, L. Van Gool, M. Vergauwen, F. Verbiest, K. Cornelis, J. Tops, and R. Koch. Visual modeling with a hand-held camera. IJCV, 59(3):207--232, 2004.
[35]
J. L. Schonberger and J.-M. Frahm. Structure-from-motion ¨ revisited. In CVPR, 2016.
[36]
T. Shen, J. Wang, T. Fang, S. Zhu, and L. Quan. Color correction for image-based modeling in the large. In ACCV, 2016.
[37]
T. Shen, S. Zhu, T. Fang, R. Zhang, and L. Quan. Graphbased consistent matching for structure-from-motion. In ECCV, 2016.
[38]
K. Sim and R. Hartley. Recovering camera motion using l∞ minimization. In CVPR, 2006.
[39]
S. N. Sinha, D. Steedly, and R. Szeliski. A multi-stage linear approach to structure from motion. In ECCV-workshop RMLE, 2010.
[40]
N. Snavely, S. M. Seitz, and R. Szeliski. Phototourism: exploringimagecollectionsin3d. SIGGRAPH, 2006.
[41]
N. Snavely, S. M. Seitz, and R. Szeliski. Skeletal graphs for efficient structure from motion. In CVPR, 2008.
[42]
C. Sweeney, V. Fragoso, T. Hollerer, and M. Turk. Large ¨ scale SFM with the distributed camera model. In 3DV, 2016.
[43]
C. Sweeney, T. Sattler, T. Hollerer, M. Turk, and M. Pollefeys. Optimizing the viewing graph for structure-frommotion. In ICCV, 2015.
[44]
B. Triggs, P. F. McLauchlan, R. I. Hartley, and A. W. Fitzgibbon. Bundle adjustment - a modern synthesis. In LNCS, 2000.
[45]
J. Wang, T. Fang, Q. Su, S. Zhu, J. Liu, S. Cai, C. Tai, and L. Quan. Image-based building regularization using structural linear features. TVCG, 22(6):1760--1772, 2016.
[46]
K. Wilson, D. Bindel, and N. Snavely. When is rotations averaging hard? In ECCV, 2016.
[47]
K. Wilson and N. Snavely. Robust global translations with 1dSFM. In ECCV, 2014.
[48]
C. Wu. Towards linear-time incremental structure from motion. In 3DV, 2013.
[49]
Y. Yao, S. Li, S. Zhu, T. Fang, H. Deng, and L. Quan. Relative camera refinement for accurate dense reconstruction. In 3DV, 2017.
[50]
C. Zach, A. Irschara, and H. Bischof. What can missing correspondences tell us about 3d structure and motion? In CVPR, 2008.
[51]
S. Zhu, T. Shen, L. Zhou, R. Zhang, J. Wang, T. Fang, and L. Quan. Parallel structure from motion from local increment to global averaging. In arXiv:1702.08601, 2017.
[52]
Zhu, S., Zhang, R., Zhou, L., Shen, T., Fang, T., Tan, P., Quan, L., 2018. Very large-scale global SFM by distributed motion averaging, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4568--4577.
[53]
Olsson C., Enqvist O. Non-sequential structure from motion, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), Barcelona, 2011, pp. 264--271,
[54]
Olsson C., Enqvist O. Stable Structure from Motion for Unordered Image Collections. In: Heyden A., Kahl F. (eds) Image Analysis. SCIA 2011.
[55]
Slater J.A., Malys S. (1998) WGS 84 --- Past, Present and Future. In: Brunner F.K. (eds) Advances in Positioning and Reference Frames. International Association of Geodesy Symposia, vol 118. Springer, Berlin, Heidelberg.
[56]
Schönberger, J.L., Frahm, J., 2016. Structure-from-motion revisited, in: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104--4113.
[57]
Sweeney, C., Höllerer, T., Turk, M., 2015. Theia: A fast and scalable structure-from-motion library, in: Annual ACM Conference on Multimedia Conference, pp. 693--696.
Index Terms
- Parallel Large-Scale Structure from Motion by Distributed Averaging
Recommendations
Practical Structure and Motion from Stereo When Motion is Unconstrained
This paper describes a system which robustly estimates motion, and the 3D structure of a rigid environment, as a stereo vision platform moves through it. The system can cope with any camera motion, and any scene structure and is successful even in the ...
Multilinear Factorizations for Multi-Camera Rigid Structure from Motion Problems
Camera networks have gained increased importance in recent years. Existing approaches mostly use point correspondences between different camera views to calibrate such systems. However, it is often difficult or even impossible to establish such ...
A generic structure-from-motion framework
Special issue on omnidirectional vision and camera networksWe introduce a generic structure-from-motion approach based on a previously introduced, highly general imaging model, where cameras are modeled as possibly unconstrained sets of projection rays. This allows to describe most existing camera types ...
Comments
Information & Contributors
Information
Published In
November 2020
1202 pages
ISBN:9781450387811
DOI:10.1145/3443467
Copyright © 2020 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 01 February 2021
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
EITCE 2020
EITCE 2020: 2020 4th International Conference on Electronic Information Technology and Computer Engineering
November 6 - 8, 2020
Xiamen, China
Acceptance Rates
EITCE '20 Paper Acceptance Rate 214 of 441 submissions, 49%;
Overall Acceptance Rate 508 of 972 submissions, 52%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 49Total Downloads
- Downloads (Last 12 months)4
- Downloads (Last 6 weeks)1
Reflects downloads up to 08 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in