![](bg6.png)
(a) (b)
Figure 5: The comparison of 3D reconstruction error between low rank based methods PTA , BMM with different rank and
our method with different dictionary size on Running.
shapes in a sequential way. As a result, we showed
that our method achieved the best reconstruction per-
formance on CMU database against several existing
methods. Unlike the low rank based methods such as
BMM and PTA, increasing the number of bases will
reduce reconstruction error for our method. We be-
lieve that our method is a reasonable choice for solv-
ing NRSfM when training data is available.
REFERENCES
Agudo, A., Agapito, L., Calvo, B., and Montiel, J. (2014).
Good vibrations: A modal analysis approach for se-
quential non-rigid structure from motion. In Proceed-
ings of the IEEE Conference on Computer Vision and
Pattern Recognition, pages 1558–1565.
Agudo, A. and Moreno-Noguer, F. (2015). Simultaneous
pose and non-rigid shape with particle dynamics. In
Proceedings of the IEEE Conference on Computer Vi-
sion and Pattern Recognition, pages 2179–2187.
Akhter, I., Sheikh, Y., Khan, S., and Kanade, T. (2008).
Nonrigid structure from motion in trajectory space. In
Advances in neural information processing systems,
pages 41–48.
Akhter, I., Sheikh, Y., Khan, S., and Kanade, T. (2011).
Trajectory space: A dual representation for nonrigid
structure from motion. Pattern Analysis and Machine
Intelligence, IEEE Transactions on, 33(7):1442–
1456.
Bregler, C., Hertzmann, A., and Biermann, H. (2000). Re-
covering non-rigid 3d shape from image streams. In
Computer Vision and Pattern Recognition, 2000. Pro-
ceedings. IEEE Conference on, volume 2, pages 690–
696. IEEE.
Carlo, T. and Kanade, T. (1992). Shape and motion from
image streams under orthography: a factorization
method. International Journal of Computer Vision,
9(2):137–154.
Carnegie mellon university, . Cmu graphics lab motion cap-
ture database. http://mocap.cs.cmu.edu/.
Dai, Y., Li, H., and He, M. (2014). A simple prior-
free method for non-rigid structure-from-motion fac-
torization. International Journal of Computer Vision,
107(2):101–122.
Del Bue, A., Xavier, J., Agapito, L., and Paladini, M.
(2012). Bilinear modeling via augmented lagrange
multipliers (balm). Pattern Analysis and Machine In-
telligence, IEEE Transactions on, 34(8):1496–1508.
Fragkiadaki, K., Salas, M., Arbelaez, P., and Malik, J.
(2014). Grouping-based low-rank trajectory comple-
tion and 3d reconstruction. In Advances in Neural In-
formation Processing Systems, pages 55–63.
Garg, R., Roussos, A., and Agapito, L. (2013). Dense
variational reconstruction of non-rigid surfaces from
monocular video. In Proceedings of the IEEE Con-
ference on Computer Vision and Pattern Recognition,
pages 1272–1279.
Gotardo, P. F. and Martinez, A. M. (2011). Non-rigid struc-
ture from motion with complementary rank-3 spaces.
In Computer Vision and Pattern Recognition (CVPR),
2011 IEEE Conference on, pages 3065–3072.
Lee, H., Battle, A., Raina, R., and Ng, A. Y. (2006). Effi-
cient sparse coding algorithms. In Advances in neural
information processing systems, pages 801–808.
Paladini, M., Bartoli, A., and Agapito, L. (2010). Sequential
non-rigid structure-from-motion with the 3d-implicit
low-rank shape model. In Computer Vision–ECCV
2010, pages 15–28. Springer.
Park, H. S., Shiratori, T., Matthews, I., and Sheikh, Y.
(2010). 3d reconstruction of a moving point from a
series of 2d projections. In ECCV, pages 158–171.
Tao, L. and Matuszewski, B. (2013). Non-rigid structure
from motion with diffusion maps prior. In Proceed-
ings of the IEEE Conference on Computer Vision and
Pattern Recognition, pages 1530–1537.
Torresani, L., Hertzmann, A., and Bregler, C. (2008).
Nonrigid structure-from-motion: Estimating shape
and motion with hierarchical priors. Pattern Analy-
sis and Machine Intelligence, IEEE Transactions on,
30(5):878–892.
Xiao, J., Chai, J., and Kanade, T. (2004). A closed-form
solution to non-rigid shape and motion recovery. In
ECCV, pages 573–587.
VISAPP 2017 - International Conference on Computer Vision Theory and Applications
338