The Mumford-Shah (MS) model is an important tool for data segmentation. The previous research on piecewise constant MS segmentation model with total variation regularization pursued the shortest length of boundaries. By contrast, in this article, we propose a novel piecewise smooth Mumford-Shah segmentation model by utilizing the total generalized variation (TGV) regularization, which assumes that the feature function of a data can be approximated by the sum of a piecewise constant function and a smooth function. The newly introduced TGV regularized piecewise smooth model is effective in segmenting point cloud surfaces with irregular structures and getting the optimal boundaries rather than the shortest boundaries. We solve the piecewise smooth MS model by alternating minimization and alternating direction method of multipliers (ADMM), where the subproblems are solved by either the closed-form solution or numerical packages. Our algorithm is discussed from several aspects, and comparisons with the piecewise constant MS model. Experimental results show that our TGV regularized segmentation method can yield competitive results when compared to other approaches.

Shanqiang Wang, Huayan Zhang. Total Generalized Variation Regularized Piecewise Smooth Mumford-Shah Point Cloud Surface Segmentation. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 5: 44-54. https://doi.org/10.25236/AJCIS.2024.070506.

[1] A. Nguyen and B. Le. 3d point cloud segmentation: A survey. In 2013 6th IEEE conference on robotics, automation and mechatronics (RAM), pages 225230. IEEE, 2013.

[2] E. Grilli, F. Menna, and F. Remondino. A review of point clouds segmentation and classification algorithms. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42:339344, 2017.

[3] O. Kaick, N. Fish, Y. Kleiman, S. Asa, and D. Cohen-Or. Shape segmentation by approximate convexity analysis. ACM Trans. Graph., 34(1), 2014.

[4] C. R. Qi, H. Su, K. Mo, and L. J. Guibas. Pointnet: Deep learning on point sets for 3d classication and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652660, 2017.

[5] X. Li, Y. J. Zhang, X. Yang, H. Xu, and G. Xu. Point cloud surface segmentation based on volumetric eigenfunctions of the laplace-beltrami operator. Computer Aided Geometric Design, 71:157175, 2019.

[6] M. Xu, Z. Zhou, and Y. Qiao. Geometry sharing network for 3d point cloud classification and segmentation. In Proceedings of the AAAI Conference on Articial Intelligence, volume 34, pages 1250012507, 2020.

[7] H. Zhang and C. Wang. Total variation diffusion and its application in shape decom position. Computers & Graphics, 90:95107, 2020.

[8] S. Qiu, S. Anwar, and N. Barnes. Dense-resolution network for point cloud classification and segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 38133822, 2021.

[9] L. Tang, Y. Zhan, Z. Chen, B. Yu, and D. Tao. Contrastive boundary learning for point cloud segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 84898499, 2022.

[10] D. Mumford and J. Shah. Optimal approximations by piecewise smooth functions and associated variational problems. Commun. Pur. Appl. Math., 42(5):577685, 1989.

[11] A. Chambolle. Image segmentation by variational methods: Mumford and shah functional and the discrete approximations. SIAM J. Appl. Math., 55(3):827863, 1995.

[12] L. Vese and T. Chan. A multiphase level set framework for image segmentation using the mumford and shah model. International Journal of Computer Vision, 50(3):271293, 2002.

[13] J. Lie, M. Lysaker, and X.-C. Tai. A binary level set model and some applications for mumford-shah image segmentation. IEEE Trans. Image Proc., 15(5):11711181, 2006.

[14] E. Brown, T. Chan, and X. Bresson. Completely convex formulation of the chan-vese image segmentation model. Int. J. Comput. Vis., 98(1):103121, 2012.

[15] Y. Li, C. Wu, and Y. Duan. The tvp regularized mumford-shah model for image labeling and segmentation. IEEE Transactions on Image Processing, 29:70617075, 2020.

[16] C. Wu, J. Zhang, Y. Duan, and X. Tai. Augmented lagrangian method for total variation based image restoration and segmentation over triangulated surfaces. J. Sci. Comput., 50(1):145166, 2012.

[17] J. Zhang, J. Zheng, C. Wu, and J. Cai. Variational mesh decomposition. ACM Trans. Graph., 31(3):21, 2012.

[18] H. Zhang, C. Wu, J. Deng, Z. Liu, and Y. Yang. A new two-stage mesh surface seg mentation method. The Visual Computer, 34:15971615, 2018.

[19] H. Zhang, Z. He, and X. Wang. A novel mesh denoising method based on relaxed second-order total generalized variation. SIAM Journal on Imaging Sciences, 15(1):1 22, 2022.

[20] H. Zhang and P. Zhichao. Total generalized variation for triangulated surface data. Journal of Scientific Computing, 93(3):87, 2022.

[21] R. Lai, J. Liang, and H. Zhao. A local mesh method for solving pdes on point clouds. Inverse Problems & Imaging, 7(3), 2013.

[22] Y. Gu, W. Xiong, L.-L. Wang, and J. Cheng. Generalizing mumford-shah model for multiphase piecewise smooth image segmentation. IEEE Transactions on Image Processing, 26(2):942952, 2016.

[23] M. Jung. Piecewise-smooth image segmentation models with l1 data-fidelity terms. Journal of Scientific Computing, 70(3):12291261, 2017.

[24] J. Shi and J. Malik. Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 22(8):888905, 2000.

[25] W. Tong, X. Yang, M. Pan, and F. Chen. Spectral mesh segmentation via l0 gradient minimization. IEEE transactions on visualization and computer graphics, 26(4):1807 1820, 2020.

[26] C. Wu and X. Tai. Augmented lagrangian method, dual methods, and split bregman iteration for rof, vectorial tv, and high order models. SIAM J. Imaging Sci., 3(3):300 339, 2010.

[27] M. NG, P. Weiss, and X. Yuan. Solving constrained total-variation image restoration and reconstruction problems via alternating direction methods. SIAM J. Sci. Comput., 32(5):27102736, 2010.

[28] S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning, 3(1):1122, 2011.

[29] J. Lellmann and C. Schnoerr. Continuous multiclass labeling approaches and algorithms. SIAM J. Imaging Sci., 4(4):10491096, 2011.

[30] C. Michelot. A finite algorithm for finding the projection of a point onto the canonical simplex of rn. J. Optim. Theory Appl., 50(1):195200, 1986.