Current Trends in Signal Processing

Comparative Study of Structure-from-Motion Algorithms 3D Shape Reconstruction

  1. K. Punnam Chandar ✉
  2. T. Satya Savithri

Abstract

3D shape reconstruction from multiview photographs and video sequences (2D images) is an active area of research. Existing face recognition systems are based on 2D facial images and exhibit well-known deficiencies. Accordingly, the face recognition research is gradually shifting from classical 2D to sophisticated 3D or hybrid 2D/3D. Currently the 3D reconstruction algorithms may be grouped in to four categories. These are shape-from-X, 3D morphable model (3DMM), structure from motion (SFM) and learning based. In this paper, we introduce, discuss and analyze the recent SFM methods, depth estimation based on genetic algorithm (SM), constrained independent component analysis (cICA) and non-linear least squares modeling (NLS). We begin by introducing similarity transform, which forms the basis of SFM reconstruction techniques described here. This is followed by a review and comparison of the three methods. The characteristics of the three SFM methods are summarized in a table that should facilitate further research on this topic.

References (40)

  1. Yuille Alan L, et al. Determining Generative Mod els of Objects Under Varying Illumination : Shape and Albedo from Multiple Images Using SVD and Integrability. Int J Comput Vis . 1999; 35(3): 203–222p.
  2. Tsalakanidou Filareti, Sotiris Malassiotis, Strintzis Michael G. Face Localization and Authentication Using Color and Depth Images. IEEE Trans Image Processing . 2005; 14(2): 152–168p.
  3. Wang Yueming, Jianzhuang Liu, Xiaoou Tang. Robust 3D Face Recognition by Local Shape Difference Boosting. IEEE Trans Pattern Anal Machine Intell . 2010; 32(10): 1858–1870p. Current Trends in Signal Processing Volume 6, Issue 1 ISSN: 2277-6176(online), ISSN: 2321-4252(print) CTSP (2016) 1-10 © STM Journals 2016. All Rights Reserved Page 9
  4. Gupta Shalini, Markey Mia K, Bovik Alan C. Anthropometric 3D Face Recogni tion. Int J Comput Vis. 2010; 90(3): 331–349p.
  5. Gonzalez-Mora Jose, et al. Bilinear Active Appearance Models. 2007.
  6. Bowyer Kevin W, Kyong Chang, Patrick Flynn. A Survey of Approaches and Challenges in 3D and Multi-Modal 3D+ 2D Face Recogn ition. Comput Vis Image Underst. 2006; 101(1): 1–15p.
  7. Thelen Andrea, et al . Improvements in Shape-from-Focus for Holographic Reconstructions with Regard to Focus Operators, Neighborhood-Size, and Height Value Interpolation . IEEE Trans Image Processing: A Publi cation of the IEEE Signal Processing Society . 2009; 18(1): 151–157p.
  8. Castelán Mario, Hancock. Edwin R. Acquiring Height Data from a Single Image of a Face Using Local Shape Indicat ors. Comput Vis Image Underst . 2006; 103(1): 64–79p.
  9. Castelán Mario, Hancock Edwin R. A Simple Coupled Statistical Mod el for 3 D Face Shape Recovery. Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, IEEE. 2006; 1.
  10. Castelán Mario, Johan Van Horebeek. 3D Face Shape Approximation from Intensities Using Partial Least Squares. Computer Vision and Pattern Recognition Workshops, 2008. CVPRW'08. IEEE Computer Society Conference on. IEEE. 2008.
  11. Jiang Dalong, et al . Efficient 3D Reconstruction for Face Recognition . Pattern Recogn. 2005; 38(6): 787–798p.
  12. Romdhani Sami, Thomas Vetter. Efficient, Robust and Accurate Fitting of a 3D Morphable Model. Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, IEEE. 2003.
  13. Zhang Chongzhen, Cohen Fernand S. 3-D Face Structure Extraction and Recognition from Images Using 3-D Morphing and Distance Mapp ing. IEEE Trans Image Processing. 2002; 11(11): 1249–1259p.
  14. Tomasi Carlo, Takeo Kanade. Shape and Motion from Image Streams: A Factorization Method: Full Report on the Orthographic Case. Cornell University; 1992.
  15. Fortuna Jeff, Martinez Aleix M. Rigid Structure from Motio n from a Blind Source Separation Perspective. Int J Comput Vis. 2010; 88(3): 404–424p.
  16. Bregler Christoph, Aaron Hertzmann, Henning Biermann. Recovering Non - Rigid 3D Shape from Image Streams. Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on . IEEE. 2000; 2.
  17. Torresani Lorenzo, Aaron Hertzmann, Christoph Bregler. Nonrigid Structure - from-Motion: Estimating Shape and Motion with Hierarchical Priors. IEEE Trans Pattern Anal Machine Intell . 2008; 30(5): 878–892p.
  18. Akhter Ijaz, et al . Trajectory Space: A Dual Representation for Nonrigid Structure from Motion. IEEE Trans Pattern Anal Machine Intell. 2011; 33(7): 1442–1456p.
  19. Koo Hei -Sheung, Kin -Man Lam. Recovering the 3D Shape and Poses of Face Images Based on the Similarity Transform. Pattern Recogn Lett. 2008; 29(6): 712–723p.
  20. Song Mingli, et al . Three -Dimensional Face Reconstruction from a Single Image by a Coupled RBF Network. IEEE Trans Image Processing . 2012; 21(5): 2887 – 2897p.
  21. Castelán Mario, Puerto -Souza Gustavo A, Johan Van Horebeek. Using Subspace Multiple Linear Regre ssion for 3D Face Shape Predi ction from a Single Image. Adv Vis Comput , Springer Berlin Heidelberg. 2009; 662–673p.
  22. Li Annan, et al. Recovering 3D Facial Shape via Coupled 2D/3D Space Learning. Automatic Face and Gesture Recognition, 2008. FG'08. 8th IEEE International Conference on. IEEE. 2008.
  23. Lee Kyoung Mu, C -CJ Kuo. Shape from Shading with a Linear Triangular Element Surface Model. IEEE Trans Pattern Anal Machine Intell. 1993; 15(8): 815–822p.
  24. Horn Berthold KP. Height and Gradient from Shading. Int J Comput Vis. 1990; 5(1): 37–75p. Structure-from-Motion Algorithms 3D Shape Reconstruction Chandar and Savithri CTSP (2016) 1-10 © STM Journals 2016. All Rights Reserved Page 10
  25. Zheng Qinfen, Rama Chellappa. Estimation of Illuminant Direction, Albedo, and Shape from Shading. Computer Vision and Pattern Recognition, 1991. Proceedings CVPR'91. IEEE Computer Society Conference on . IEEE . 1991.
  26. Zhang Ruo, et al. Shape-from-Shading: A Survey. IEEE Trans Pattern Anal Machine Intell. 1999; 21(8): 690–706p.
  27. Blanz Volker, Thomas Vetter. Face Recognition Ba sed on Fitting a 3D Morphable Model . IEEE Trans Pattern Anal Machine Intell. 2003; 25(9): 1063 – 1074p.
  28. Nandy Dibyendu, Jezekiel Ben -Arie. Shape from Recognition: A Novel Approach for 3 -D Face Shape Recove ry. IEEE Trans Image Processing . 2001; 10(2): 206–217p.
  29. Ullman Shimon. The Interpretation of Visual Motion. 1979.
  30. Huang Thomas S, Lee CH. Motion and Structure from Orthographic Projections . IEEE Trans Pattern Anal Machine Intell. 1989; 11(5): 536–540p.
  31. Hu Xiaoping, Narendra Ahuja. Motion Estimation Under Orthographic Projection. IEEE Trans Robot Automat . 1991; 7(6): 848–853p.
  32. Shapiro Larry S, Andrew Zisserman, Michael Brady. 3D Motion Recove ry via Affine Epipolar Geom etry. Int J Comput Vis. 1995; 16(2): 147–182p.
  33. Xirouhakis Yiannis, Anastasios Delopoulos. Least Squares Estim ation of 3D Shape and Motion of Rigid Obje cts from their Orthographic Projections. IEEE Trans Pattern Anal Machine Intell. 2000; 22(4): 393–399p.
  34. Werman Michael, Daphna Weinshall. Similarity and Affine Invariant Distances between 2D Point Sets. IEEE Trans Pattern Anal Machine Intell. 1995; 17(8): 810–814p.
  35. Sun Zhanli, Kin -Man Lam. Depth Estimation of Face Images Base d on the Constrained ICA Model. IEEE Trans Inf Forensics Security. 2011; 6(2): 360–370p.
  36. Sun Zhan -Li, Kin -Man Lam, Qing -Wei Gao. Depth Estimation of Face Images Using the Nonlinear Least-Squares Model. IEEE Trans Image Processing . 2013; 22(1): 17–30p.
  37. Ahlberg Jörgen. An Active Model for Facial Feature Tracking. EURASIP J A dv Signal Process. 2002;1(2002): 566–571p.
  38. Xie Xudong, Kin -Man Lam. Elastic Shape-Texture Matching for Human Face Recognition. Pattern Recogn. 2008; 41(1): 396–405p.
  39. Huang De -Shuang, Jian -Xun Mi. A New Constrained Independent Component Analysis Meth od. IEEE Trans Neural Networks. 2007; 18(5): 1532–1535p.
  40. Lu Wei, Rajapakse Jagath C. ICA with Reference. Neurocomputing. 2006; 69(16): 2244–2257p. Cite this Article Punnam Chandar K, Satya Savithri T. Comparative study of structure -from- motion algorithms 3D shape reconstruction. Current Trends in Signal Processing. 2016; 6(1): 1–10p.

Read more of it

Subscribe to one journal or build your own list of several. One invoice, one payment, access for a full year.

Subscribe to journals →

Publish your article

Peer-reviewed journals across every subject, with open access options. Send your manuscript to the right editor today.

Publish with us → Calculate your APC
Support