Noisy depth maps fusion for multiview stereo via matrix completion

IEEE Journal on Selected Topics in Signal Processing

Volumn 6, Issue 5, 2012, Pages 566-582

  Deng, Yue ^a   Liu, Yebin ^a   Dai, Qionghai ^a   Zhang, Zengke ^a   Wang, Yao ^b  

^a TSINGHUA UNIVERSITY   (China)

^b POLYTECHNIC UNIVERSITY   (United States)

Author keywords

Compressive sensing; fusion; matrix completion; multiview stereo (MVS); point cloud

Indexed keywords

COMPRESSIVE SENSING; DEPTH MAP; MATRIX COMPLETION; MULTI-VIEW IMAGE; MULTI-VIEW STEREO; NOISY MATRIX; NOISY POINT; POINT CLOUD; SIGNAL PROCESSING TECHNIQUE; VISION PROBLEMS;

ALGORITHMS; CONVEX OPTIMIZATION; FUSION REACTIONS; SIGNAL PROCESSING;

CAMERAS;

EID: 84865417152     PISSN: 19324553     EISSN: None     Source Type: Journal    
DOI: 10.1109/JSTSP.2012.2195472     Document Type: Article

References (51)

1. S. Ma, D. Goldfarb, and L. Chen, "Fixed point and bregman iterative methods for matrix rank minimization," Math. Program. vol. 128, pp. 321-353, 2011 [Online]. Available: http://dx.doi.org/10.1007/s10107- 009-0306-5
2. E. Candès and Y. Plan, "Matrix completion with noise," Proc. IEEE, vol. 98, no. 6, pp. 925-936, Jun. 2010.
3. E. J. Candès, X. Li, Y. Ma, and J. Wright, "Robust principal component analysis?," J. ACM, vol. 59, no. 3, pp. 1-37, May 2011.
4. M. Fazel, "Matrix rank minimization with applications," Ph.D. dissertation, Stanford Univ., Stanford, CA, Mar. 2002.
5. E. J. Candès, M. Wakin, and S. Boyd, "Enhancing sparsity by reweighted minimization," J. Fourier Anal. Appl., pp. 877-905.
6. K. Lange, D. R. Hunter, and I. Yang, "Optimization transfer using surrogate objective functions," J. Comput. Graph. Statist., vol. 9, pp. 1-59, 2000.
7. S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, "Distributed optimization and statistical learning via the alternating direction method of multipliers," Found. Trends Mach. Learn., vol. 3, no. 1, pp. 1-123, 2010.
8. Z. Lin, M. Chen, and Y. Ma, The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices, Tech. Rep. arXiv:1009.5055v2, Mar. 2011.
9. Y. Deng, Q. Dai, R. Liu, Z. Zhang, and S. Hu, "Low-rank structure learning via log-sum heuristic recovery," 2012, Preprint in arXiv 1012. 1919.
10. S. Seitz, B. Curless, J. Diebel, D. Scharstein, and R. Szeliski, "A comparison and evaluation of multi-viewstereo reconstruction algorithms," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn., Jun. 2006, vol. 1, pp. 519-528.
11. V. Kolmogorov and R. Zabih, "Multi-camera scene reconstruction via graph cuts," in Eur. Conf. Comput. Vis., 2002, pp. 82-96.
12. G. Vogiatzis, P. Torr, and R. Cipolla, "Multi-view stereo via volumetric graph-cuts," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn. CVPR, Jun. 2005, vol. 2, pp. 391-398, vol. 2.
13. Y. Furukawa and J. Ponce, "Accurate, dense, and robust multiview stereopsis," IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 8, pp. 1362-1376, Aug. 2010.
14. M. Goesele, N. Snavely, B. Curless, H. Hoppe, and S. Seitz, "Multiview stereo for community photo collections," in Proc. IEEE 11th Int. Conf. Comput. Vis. ICCV '07, Oct. 2007, pp. 1-8.
15. M. Habbecke and L. Kobbelt, "A surface-growing approach to multiview stereo reconstruction," in Proc. IEEE Conf. Comput. Vis. Pattern Recogn. CVPR'07, Jun. 2007, pp. 1-8.
16. J.-P. Pons, R. Keriven, and O. Faugeras, "Modelling dynamic scenes by registering multi-view image sequences," in Proc. IEEE Comput. Soc. Conf. Comput. Vision Pattern Recogn. CVPR '05, Jun. 2005, vol. 2, pp. 822-827, vol. 2.
17. A. Zaharescu, E. Boyer, and R. Horaud, "Topology-adaptive mesh deformation for surface evolution, morphing, and multiview reconstruction," IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 4, pp. 823-837, Apr. 2011.
18. Y. Liu, Q. Dai, and W. Xu, "A point cloud based multi-view stereo algorithm for free-viewpoint video," IEEE Trans. Visualiz. Comput. Graphics, vol. 16, no. 3, pp. 407-418, May-Jun. 2010.
19. P. Merrell, A. Akbarzadeh, L. Wang, P. Mordohai, J. M. Frahm, R. Yang, D. Nister, and M. Pollefeys, "Real-time visibility-based fusion of depth maps," in Proc. IEEE 11th Int. Conf. Comput. Vis. ICCV '07, 2007, vol. 14, no. 21, pp. 1-8.
20. M. Goesele, B. Curless, and S. M. Seitz, "Multi-view stereo revisited," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn. - Vol. 2 Ser. CVPR'06, Washington, DC, 2006, pp. 2402-2409 [Online]. Available: http://dx.doi.org/10.1109/CVPR.2006.199
21. J. Li, E. Li, Y. Chen, L. Xu, and Y. Zhang, "Bundled depth-map merging for multi-view stereo," in Proc. IEEE Conf. Comput. Vis. Pattern Recogn. (CVPR), Jun. 2010, pp. 2769-2776.
22. N. Campbell, G. Vogiatzis, C. Hernandez, and R. Cipolla, "Using multiple hypotheses to improve depth-maps for multi-viewstereo," in Proc. Eur. Conf. Comput. Vis., 2008, vol. 1, pp. 766-779.
23. P. Gargallo and P. Sturm, "Bayesian 3d modeling from images using multiple depth maps," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn. CVPR '05, 2005, vol. 2, pp. 885-891.
24. Y. Liu, X. Cao, Q. Dai, and W. Xu, "Continuous depth estimation for multi-view stereo," in Proc. IEEE Conf. Comput. Vis. Pattern Recogn. CVPR '09, Jun. 2009, pp. 2121-2128.
25. D. Bradley, T. Boubekeur, and W. Heidrich, "Accurate multi-view reconstruction using robust binocular stereo and surface meshing," in Proc. IEEE Conf. Comput. Vis. Pattern Recogn, 2008. CVPR 2008, Jun. 2008, pp. 1-8.
26. C. Zach, "Fast and high quality fusion of depth maps," in Proc. Int. Symp. 3D Data Process., Visualiz. Transmiss. (3DPVT), 2008.
27. J. Rennie and N. Srebro, "Fast maximum margin matrix factorization for collaborative prediction," in Proc. 22nd Int. Conf. Mach. Learn., ACM, 2005, pp. 713-719.
28. E. J. Candès and B. Recht, "Exact matrix completion via convex optimization," Found. Comput. Math., pp. 717-772, 2008.
29. K. Toh and S. Yun, "An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems," Pacific J. Optimiz., vol. 6, no. 615-640, p. 15, 2010.
30. Z. Zhou, X. Li, J. Wright, E. J. Candès, and Y. Ma, "Stable principal component pursuit," in Proc. Int. Symp. Inf. Theory, Jun. 2010.
31. D. Goldberg, D. Nichols, B. M. Oki, and D. Terry, "Using collaborative filtering to weave an information tapestry," Commun. ACM, vol. 35, no. 12, pp. 61-70, 1992.
32. P. Biswas, T. C. Lian, T. C. Wang, and Y. Ye, "Semidefinite programming based algorithms for sensor network localization," ACM Trans. Sens. Netw., vol. 2, no. 2, pp. 188-220, 2006. (Pubitemid 44188494)
33. K. Mohan and M. Fazel, "Reweighted nuclear norm minimization with application to system identification," in Proc. Amer. Control Conf., 2010.
34. J.Wang, Y. Dong, X. Tong, Z. Lin, and B. Guo, "Kernel nystrm method for light transport," ACM Trans. Graph. vol. 28, pp. 29:1-29:10, Jul. 2009 [Online]. Available: http://doi.acm.org/10.1145/1531326. 1531335
35. R. Garg, H. Du, S. Seitz, and N. Snavely, "The dimensionality of scene appearance," in Proc. IEEE 12th Int. Conf. Comput. Vis., 29 2009-Oct. 2 2009, pp. 1917-1924.
36. Y. Deng, Q. Dai, and Z. Zhang, "Graph laplace for partially occluded face completion and recognition," IEEE Trans. Image Process., vol. 20, no. 8, pp. 2329-2338, Aug. 2011.
37. Y. Peng, A. Ganesh, J. Wright, and Y. Ma, "RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images," in Proc. CVPR, 2010.
38. C. Fu, X. Ji, and Q. Dai, "Adaptive compressed sensing recovery utilizing the property of signals autocorrelations," IEEE Trans. Image Process., vol. 21, no. 5, pp. 2369-2378, May 2011.
39. T. Brox, A. Bruhn, N. Papenberg, and J.Weickert, High Accuracy Optical Flow Estimation Based on a Theory for Warping. New York: Springer, 2004, pp. 25-36.
40. F. Huguet and F. Devernay, "A variational method for scene flow estimation from stereo sequences," in Proc. IEEE 11th Int. Conf. Comput. Vis. ICCV '07, Oct. 2007, pp. 1-7.
41. H. Zou and T. Hastie, "Regularization and variable selection via the elastic net," J. R. Statist. Soc. B, vol. 67, pp. 301-320, 2005. (Pubitemid 40465877)
42. A. Beck and M. Teboulle, "A fast iterative shrinkage-thresholding algorithm for linear inverse problems.," SIAM J. Imag. Sci., vol. 2, no. 1, pp. 183-202.
43. M. Lees, "Iterative reweighted least squares for matrix rank minimization," Math. Comput., vol. 16, no. 77, pp. 70-75, 1963.
44. S. Ma, D. Goldfarb, and L. Chen, "Fixed point and bregman iterative methods for matrix rank minimization," Math. Program., vol. 128, no. 1, pp. 321-353, 2011.
45. [Online]. Available: http://cvlab.epfl.ch/strecha/multiview
46. C. Strecha, W. von Hansen, L. V. Gool, and U. T. P. Fua, "On benchmarking camera calibration and multi-view stereo for high resolution imagery," in Proc. IEEE Conf. Comput. Vis. Pattern Recogn. CVPR '09, 2008, pp. 1-8.
47. Z. Lin, R. Liu, and Z. Su, "Linearized alternating direction method with adaptive penalty for low-rank representation," in Proc. Adv. Neural Inf. Process. Syst., 2011.
48. J.Yang and X.Yuan, "Linearized augmented lagrangian and alternating direction methods for nuclear norm minimization," Math. Comp., 2012, to be published.
49. G. Liu, Z. Lin, S. Yan, J. Sun, Y. Yu, and Y. Ma, "Robust recovery of subspace structures by low-rank representation," IEEE Trans. Pattern Anal. Mach. Intell., 2012, to be published.
50. M. Kazhdan, M. Bolitho, and H. Hoppe, "Poisson surface reconstruction," in Proc. 4th Eurographics Symp. Geometry Process., Ser. SGP'06, Aire-la-Ville, Switzerland, 2006, pp. 61-70 [Online]. Available: http://portal.acm.org/citation.cfm?id=1281957.1281965, Switzerland: Eurographics Association.
51. [Online]. Available: http://vision.middlebury.edu/mview/