Abstract
This paper advocates the use of organic priors in classical non-rigid structure from motion (NRSfM). By organic priors, we mean invaluable intermediate prior information intrinsic to the NRSfM matrix factorization theory. It is shown that such priors reside in the factorized matrices, and quite surprisingly, existing methods generally disregard them. The paper’s main contribution is to put forward a simple, methodical, and practical method that can effectively exploit such organic priors to solve NRSfM. The proposed method does not make assumptions other than the popular one on the low-rank shape and offers a reliable solution to NRSfM under orthographic projection. Our work reveals that the accessibility of organic priors is independent of the camera motion and shape deformation type. Besides that, the paper provides insights into the NRSfM factorization—both in terms of shape and motion—and is the first approach to show the benefit of single rotation averaging for NRSfM. Furthermore, we outline how to effectively recover motion and non-rigid 3D shape using the proposed organic prior based approach and demonstrate results that outperform prior-free NRSfM performance by a significant margin. Finally, we present the benefits of our method via extensive experiments and evaluations on several benchmark datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See, however, C. Tomasi and T. Kanade, pp. 137–154, IJCV (1992) for the original matrix factorization theory for shape and motion estimation, although devoted to the rigid SfM problem [49].
- 2.
pinv() symbolizes Moore-Penrose inverse of a matrix, also known as pseudoinverse.
- 3.
- 4.
filter if sample is too far to the reference rotation after registration.
- 5.
After registration, if samples are filtered out due to its distance from the reference rotation (more than \(\delta \)), then per frame rotations is less than K.
- 6.
For more discussion on partial sum minimization of singular values, cf. the supplementary material. For a comprehensive theory refer to [40].
- 7.
References
Aanæs, H., Kahl, F.: Estimation of deformable structure and motion. In: Proceedings of the Vision and Modelling of Dynamic Scenes Workshop, vol. 2, pp. 3. Citeseer (2002)
Akhter, I., Sheikh, Y., Khan, S.: In defense of orthonormality constraints for nonrigid structure from motion. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 1534–1541. IEEE (2009)
Akhter, I., Sheikh, Y., Khan, S., Kanade, T.: Nonrigid structure from motion in trajectory space. In: Advances in Neural Information Processing Systems, pp. 41–48 (2008)
Akhter, I., Sheikh, Y., Khan, S., Kanade, T.: Trajectory space: a dual representation for nonrigid structure from motion. IEEE Trans. Pattern Anal. Mach. Intell. 33(7), 1442–1456 (2011)
Ansari, M.D., Golyanik, V., Stricker, D.: Scalable dense monocular surface reconstruction. In: 2017 International Conference on 3D Vision (3DV), pp. 78–87. IEEE (2017)
Bartoli, A., Gay-Bellile, V., Castellani, U., Peyras, J., Olsen, S., Sayd, P.: Coarse-to-fine low-rank structure-from-motion. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends® Mach. Learn. 3(1), 1–122 (2011)
Brand, M.: A direct method for 3D factorization of nonrigid motion observed in 2D. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 2, pp. 122–128. IEEE (2005)
Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 690–696. IEEE (2000)
Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Numerical Geometry Of Non-rigid Shapes. Springer Science & Business Media, Heidelberg (2008)
Cabral, R., De la Torre, F., Costeira, J.P., Bernardino, A.: Unifying nuclear norm and bilinear factorization approaches for low-rank matrix decomposition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2488–2495 (2013)
Dai, Y., Li, H., He, M.: A simple prior-free method for non-rigid structure-from-motion factorization. In: Computer Vision and Pattern Recognition (CVPR), pp. 2018–2025. IEEE (2012)
Dai, Y., Li, H., He, M.: A simple prior-free method for non-rigid structure-from-motion factorization. Int. J. Comput. Vision 107(2), 101–122 (2014). https://doi.org/10.1007/s11263-013-0684-2
Fayad, J., Agapito, L., Del Bue, A.: Piecewise quadratic reconstruction of non-rigid surfaces from monocular sequences. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 297–310. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_22
Garg, R., Roussos, A., Agapito, L.: Dense variational reconstruction of non-rigid surfaces from monocular video. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1272–1279 (2013)
Garg, R., Roussos, A., Agapito, L.: A variational approach to video registration with subspace constraints. Int. J. Comput. Vision 104(3), 286–314 (2013). https://doi.org/10.1007/s11263-012-0607-7
Golyanik, V., Jonas, A., Stricker, D., Theobalt, C.: Intrinsic dynamic shape prior for dense non-rigid structure from motion. In: 2020 International Conference on 3D Vision (3DV), pp. 692–701. IEEE (2020)
Gotardo, P.F., Martinez, A.M.: Computing smooth time trajectories for camera and deformable shape in structure from motion with occlusion. IEEE Trans. Pattern Anal. Mach. Intell. 33(10), 2051–2065 (2011)
Gotardo, P.F., Martinez, A.M.: Kernel non-rigid structure from motion. In: IEEE International Conference on Computer Vision, pp. 802–809. IEEE (2011)
Gotardo, P.F., Martinez, A.M.: Non-rigid structure from motion with complementary rank-3 spaces. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3065–3072. IEEE (2011)
Graßhof, S., Brandt, S.S.: Tensor-based non-rigid structure from motion. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3011–3020 (2022)
Hartley, R., Aftab, K., Trumpf, J.: L1 rotation averaging using the weiszfeld algorithm. In: CVPR 2011, pp. 3041–3048. IEEE (2011)
Hartley, R., Trumpf, J., Dai, Y., Li, H.: Rotation averaging. Int. J. Comput. Vision 103(3), 267–305 (2013). https://doi.org/10.1007/s11263-012-0601-0
Iglesias, J.P., Olsson, C., Valtonen Örnhag, M.: Accurate optimization of weighted nuclear norm for non-rigid structure from motion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 21–37. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58583-9_2
Jensen, S.H.N., Doest, M.E.B., Aanæs, H., Del Bue, A.: A benchmark and evaluation of non-rigid structure from motion. Int. J. Comput. Vision (IJCV) 129(4), 882–899 (2021). https://doi.org/10.1007/s11263-020-01406-y
Kumar, S.: Jumping manifolds: geometry aware dense non-rigid structure from motion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5346–5355 (2019)
Kumar, S.: Non-rigid structure from motion. Ph.D. thesis, College of Engineering & Computer Science, The Australian National University (2019)
Kumar, S.: Non-rigid structure from motion: prior-free factorization method revisited. In: Winter Conference on Applications of Computer Vision (WACV 2020), pp. 51–60 (2020)
Kumar, S., Cherian, A., Dai, Y., Li, H.: Scalable dense non-rigid structure-from-motion: a Grassmannian perspective. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 254–263 (2018)
Kumar, S., Dai, Y., Li, H.: Spatio-temporal union of subspaces for multi-body non-rigid structure-from-motion. Pattern Recogn. 71, 428–443 (2017)
Kumar, S., Dai, Y., Li, H.: Multi-body non-rigid structure-from-motion. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 148–156. IEEE (2016)
Kumar, S., Dai, Y., Li, H.: Monocular dense 3D reconstruction of a complex dynamic scene from two perspective frames. In: IEEE International Conference on Computer Vision, pp. 4649–4657 (2017)
Kumar, S., Dai, Y., Li, H.: Superpixel soup: monocular dense 3D reconstruction of a complex dynamic scene. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1705–1717 (2019)
Kumar, S., Ghorakavi, R.S., Dai, Y., Li, H.: Dense depth estimation of a complex dynamic scene without explicit 3D motion estimation. arXiv preprint arXiv:1902.03791 (2019)
Kumar, S., Van Gool, L., de Oliveira, C.E., Cherian, A., Dai, Y., Li, H.: Dense non-rigid structure from motion: a manifold viewpoint. arXiv preprint arXiv:2006.09197 (2020)
Lee, M., Cho, J., Choi, C.H., Oh, S.: Procrustean normal distribution for non-rigid structure from motion. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1280–1287 (2013)
Lee, M., Cho, J., Oh, S.: Consensus of non-rigid reconstructions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4670–4678 (2016)
Lee, S.H., Civera, J.: Robust single rotation averaging. arXiv preprint arXiv:2004.00732 (2020)
Matthews, I., Xiao, J., Baker, S.: 2D vs. 3D deformable face models: representational power, construction, and real-time fitting. Int. J. Comput. Vision 75(1), 93–113 (2007). https://doi.org/10.1007/s11263-007-0043-2
Oh, T.H., Tai, Y.W., Bazin, J.C., Kim, H., Kweon, I.S.: Partial sum minimization of singular values in robust PCA: algorithm and applications. IEEE Trans. Pattern Anal. Mach. Intell. 38(4), 744–758 (2016)
Ornhag, M.V., Iglesias, J.P., Olsson, C.: Bilinear parameterization for non-separable singular value penalties. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3897–3906 (2021)
Paladini, M., Del Bue, A., Stosic, M., Dodig, M., Xavier, J., Agapito, L.: Factorization for non-rigid and articulated structure using metric projections. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2898–2905. IEEE (2009)
Rabaud, V., Belongie, S.: Re-thinking non-rigid structure from motion. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
Recht, B., Fazel, M., Parrilo, P.A.: Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Rev. 52(3), 471–501 (2010)
Russell, C., Fayad, J., Agapito, L.: Energy based multiple model fitting for non-rigid structure from motion. In: CVPR 2011, pp. 3009–3016. IEEE (2011)
Salzmann, M., Fua, P.: Deformable surface 3D reconstruction from monocular images. Synth. Lect. Comput. Vision 2(1), 1–113 (2010)
Sidhu, V., Tretschk, E., Golyanik, V., Agudo, A., Theobalt, C.: Neural dense non-rigid structure from motion with latent space constraints. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 204–222. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_13
Taylor, J., Jepson, A.D., Kutulakos, K.N.: Non-rigid structure from locally-rigid motion. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2761–2768. IEEE (2010)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. Int. J. Comput. Vision 9(2), 137–154 (1992). https://doi.org/10.1007/BF00129684
Torresani, L., Hertzmann, A., Bregler, C.: Nonrigid structure-from-motion: estimating shape and motion with hierarchical priors. IEEE Trans. Pattern Anal. Mach. Intell. 30(5), 878–892 (2008)
Torresani, L., Hertzmann, A., Bregler, C.: Learning non-rigid 3D shape from 2D motion. In: Advances in Neural Information Processing Systems, pp. 1555–1562 (2004)
Valmadre, J., Sridharan, S., Denman, S., Fookes, C., Lucey, S.: Closed-form solutions for low-rank non-rigid reconstruction. In: 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1–6. IEEE (2015)
Xiao, J., Chai, J., Kanade, T.: A closed-form solution to non-rigid shape and motion recovery. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 573–587. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24673-2_46
Zhu, Y., Huang, D., De La Torre, F., Lucey, S.: Complex non-rigid motion 3D reconstruction by union of subspaces. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1542–1549 (2014)
Acknowledgement
The authors thank Google for their generous gift (ETH Zürich Foundation, 2020-HS-411).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kumar, S., Van Gool, L. (2022). Organic Priors in Non-rigid Structure from Motion. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13662. Springer, Cham. https://doi.org/10.1007/978-3-031-20086-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-20086-1_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20085-4
Online ISBN: 978-3-031-20086-1
eBook Packages: Computer ScienceComputer Science (R0)