Abstract
With the recent advances in data acquisition techniques, the compression of various dynamic mesh sequence data has become an important topic in the computer graphics community. In this article, we present a new spatio-temporal segmentation-based approach for the adaptive compression of the dynamic mesh sequences. Given an input dynamic mesh sequence, we first compute an initial temporal cut to obtain a small subsequence by detecting the temporal boundary of dynamic behavior. Then, we apply a two-stage vertex clustering on the resulting subsequence to classify the vertices into groups with optimal intra-affinities. After that, we design a temporal segmentation step based on the variations of the principal components within each vertex group prior to performing a PCA-based compression. Furthermore, we apply an extra step on the lossless compression of the PCA bases and coefficients to gain more storage saving. Our approach can adaptively determine the temporal and spatial segmentation boundaries to exploit both temporal and spatial redundancies. We have conducted extensive experiments on different types of 3D mesh animations with various segmentation configurations. Our comparative studies show the advantages of our approach for the compression of 3D mesh animations.
- Andreas A. Vasilakis and Ioannis Fudos. 2014. Pose partitioning for multi-resolution segmentation of arbitrary mesh animations. Comput. Graph. For., Vol. 33. Wiley Online Library, 293--302.Google Scholar
- Marc Alexa and Wolfgang Müller. 2000. Representing animations by principal components. Comput. Graph. For. 19, 3 (2000), 411--418.Google Scholar
- Oscar Kin-Chung Au, Chiew-Lan Tai, Hung-Kuo Chu, Daniel Cohen-Or, and Tong-Yee Lee. 2008. Skeleton extraction by mesh contraction. ACM Trans. Graph., Vol. 27. 44.Google Scholar
- Jernej Barbic, Alla Safonova, Jiayu Pan, Christos Faloutsos, Jessica K. Hodgins, and Nancy S. Pollard. 2004. Segmenting motion capture data into distinct behaviors. In Proceedings of Graphics Interface 2004 (GI'04). Canadian Human-Computer Communications Society, Waterloo, CAN, 185--194.Google Scholar
- Philippe Beaudoin, Pierre Poulin, and Michiel van de Panne. 2007. Adapting wavelet compression to human motion capture clips. In Proceedings of the Graphics Interface Conference. 313--318.Google Scholar
- Siddhartha Chattopadhyay, Suchendra M. Bhandarkar, and Kang Li. 2007. Human motion capture data compression by model-based indexing: A power aware approach. IEEE Trans. Vis. Comput. Graph. 13, 1 (2007), 5--14.Google Scholar
Digital Library
- Chengju Chen, Qing Xia, Shuai Li, Hong Qin, and Aimin Hao. 2018. High-fidelity compression of dynamic meshes with fine details using piece-wise manifold harmonic bases. In Proceedings of the Computer Graphics Conference. 23--32.Google Scholar
Digital Library
- Jiong Chen, Yicun Zheng, Ying Song, Hanqiu Sun, Hujun Bao, and Jin Huang. 2017. Cloth compression using local cylindrical coordinates. Vis. Comput. 33, 6–8 (2017), 801--810.Google Scholar
Digital Library
- Xiaobai Chen, Aleksey Golovinskiy, and Thomas A. Funkhouser. 2009. A benchmark for 3D mesh segmentation. In ACM Trans. Graph., Vol. 28. 73.Google Scholar
Digital Library
- Frederic Cordier and Nadia Magnenatthalmann. 2005. A data-driven approach for real-time clothes simulation. Comput. Graph. For. 24, 2 (2005), 173--183.Google Scholar
- Edilson de Aguiar, Christian Theobalt, Sebastian Thrun, and Hans-Peter Seidel. 2008. Automatic conversion of mesh animations into skeleton-based animations. Comput. Graph. For. 27, 2 (2008), 389--397.Google Scholar
- Peter Deutsch and Jean-Loup Gailly. 1996. ZLIB compressed data format specification version 3.3. RFC 1950 (1996), 1--11.Google Scholar
Digital Library
- Amirhossein Firouzmanesh, Irene Cheng, and Anup Basu. 2011. Perceptually guided fast compression of 3-D motion capture data. IEEE Trans. Multimedia 13, 4 (2011), 829--834.Google Scholar
Digital Library
- David George, Xianghua Xie, Yu-Kun Lai, and Gary K. L. Tam. 2018. A deep learning driven active framework for segmentation of large 3D shape collections. arXiv preprint arXiv:1807.06551 (2018).Google Scholar
- David George, Xianghua Xie, and Gary K. L. Tam. 2018. 3D mesh segmentation via multi-branch 1D convolutional neural networks. Graphical Models 96 (2018), 1--10.Google Scholar
Cross Ref
- Dian Gong, Gérard Medioni, Sikai Zhu, and Xuemei Zhao. 2012. Kernelized temporal cut for online temporal segmentation and recognition. In Proceedings of the European Conference on Computer Vision. Springer, 229--243.Google Scholar
Digital Library
- Qin Gu, Jingliang Peng, and Zhigang Deng. 2009. Compression of human motion capture data using motion pattern indexing. Comput. Graph. For. 28, 1 (2009), 1--12.Google Scholar
Digital Library
- Igor Guskov and Andrei Khodakovsky. 2004. Wavelet compression of parametrically coherent mesh sequences. In Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation. Eurographics Association, 183--192.Google Scholar
Digital Library
- Mohammadali Hajizadeh and Hossein Ebrahimnezhad. 2016. Predictive compression of animated 3D models by optimized weighted blending of key-frames. Comput. Anim. Virt. Worlds 27, 6 (2016), 556--576.Google Scholar
Digital Library
- Toshiki Hijiri, Kazuhiro Nishitani, Tim Cornish, Toshiya Naka, and Shigeo Asahara. 2000. A spatial hierarchical compression method for 3D streaming animation. In Proceedings of the Symposium on Virtual Reality Modeling Language. 95--101.Google Scholar
Digital Library
- Thomas Hofmann, Bernhard Scholkopf, and Alexander J. Smola. 2008. Kernel methods in machine learning. Ann. Statist. 36, 3 (2008), 1171--1220.Google Scholar
Cross Ref
- Junhui Hou, Lap Pui Chau, Nadia Magnenat-Thalmann, and Ying He. 2017. Sparse low-rank matrix approximation for data compression. IEEE Trans. Circ. Syst. Video Technol. 27, 5 (2017), 1043--1054.Google Scholar
Digital Library
- David A. Huffman. 1952. A method for the construction of minimum-redundancy codes. Proc. IRE 40, 9 (1952), 1098--1101.Google Scholar
Cross Ref
- Doug L. James and Christopher D. Twigg. 2005. Skinning mesh animations. In Proceedings of the International Conference on Computer Graphics and Interactive Techniques 24, 3 (2005), 399--407.Google Scholar
- Evangelos Kalogerakis, Aaron Hertzmann, and Karan Singh. 2010. Learning 3D mesh segmentation and labeling. In Proceedings of the International Conference on Computer Graphics and Interactive Techniques 29, 4 (2010), 102.Google Scholar
Digital Library
- Zachi Karni and Craig Gotsman. 2004. Compression of soft-body animation sequences. Comput. Graph. 28, 1 (2004), 25--34.Google Scholar
Cross Ref
- Ladislav Kavan, Peter-Pike J. Sloan, and Carol O’Sullivan. 2010. Fast and efficient skinning of animated meshes. Comput. Graph. For. 29, 2 (2010), 327--336.Google Scholar
- Murtaza Ali Khan. 2016. An efficient algorithm for compression of motion capture signal using multidimensional quadratic Bézier curve break-and-fit method. Multidimen. Syst. Sig. Proc. 27, 1 (2016), 121--143.Google Scholar
Digital Library
- Choong-Hoon Kwak and Ivan V. Bajic. 2011. Hybrid low-delay compression of motion capture data. In Proceedings of the IEEE International Conference on Multimedia and Expo. 1--6.Google Scholar
- Aris S. Lalos, Andreas A. Vasilakis, Anastasios Dimas, and Konstantinos Moustakas. 2017. Adaptive compression of animated meshes by exploiting orthogonal iterations. Vis. Comput. 33, 6–8 (2017), 1--11.Google Scholar
Digital Library
- Binh Huy Le and Zhigang Deng. 2014. Robust and accurate skeletal rigging from mesh sequences. ACM Trans. Graph. 33, 4 (2014), 1--10.Google Scholar
Digital Library
- Pai-Feng Lee, Chi-Kang Kao, Juin-Ling Tseng, Bin-Shyan Jong, and Tsong-Wuu Lin. 2007. 3D animation compression using affine transformation matrix and principal component analysis. IEICE Trans. Inf. Syst. 90, 7 (2007), 1073--1084.Google Scholar
Digital Library
- Tong-Yee Lee, Yu-Shuen Wang, and Tai-Guang Chen. 2006. Segmenting a deforming mesh into near-rigid components. Vis. Comput. 22, 9 (24 Aug. 2006), 729. DOI:https://doi.org/10.1007/s00371-006-0059-6Google Scholar
- Tong Yee Lee, Yu Shuen Wang, and Tai Guang Chen. 2006. Segmenting a deforming mesh into near-rigid components. Vis. Comput. 22, 9–11 (2006), 729.Google Scholar
Digital Library
- Xin Liu, Zaiwen Wen, and Yin Zhang. 2012. Limited memory block Krylov subspace optimization for computing dominant singular value decompositions. Siam J. Sci. Comput. 35, 3 (2012), 1641--1668.Google Scholar
Cross Ref
- Guoliang Luo, Frederic Cordier, and Hyewon Seo. 2013. Compression of 3D mesh sequences by temporal segmentation. Comput. Anim. Virt. Worlds 24, 3–4 (2013), 365--375.Google Scholar
Cross Ref
- Guoliang Luo, Zhigang Deng, Xiaogang Jin, Xin Zhao, Wei Zeng, Wenqiang Xie, and Hyewon Seo. 2019. 3D mesh animation compression based on adaptive spatio-temporal segmentation. In Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games. 10.Google Scholar
Digital Library
- Guoliang Luo, Gang Lei, Yuanlong Cao, Qinghua Liu, and Hyewon Seo. 2017. Joint entropy-based motion segmentation for 3D animations. Vis. Comput. 33, 10 (2017), 1279--1289.Google Scholar
Digital Library
- Adrien Maglo, Guillaume Lavoué, Florent Dupont, and Céline Hudelot. 2015. 3D mesh compression: Survey, comparisons, and emerging trends. Comput. Surv. 47, 3 (2015), 44.Google Scholar
Digital Library
- K. Mamou, T. Zaharia, F. Preteux, N. Stefanoski, and J. Ostermann. 2008. Frame-based compression of animated meshes in MPEG-4. In Proceedings of the IEEE International Conference on Multimedia and Expo. 1121--1124.Google Scholar
- Frédéric Payan and Marc Antonini. 2007. Temporal wavelet-based compression for 3D animated models. Comput. Graph. 31, 1 (2007), 77--88.Google Scholar
Digital Library
- Subramanian Ramanathan, Ashraf A. Kassim, and Tiow Seng Tan. 2008. Impact of vertex clustering on registration-based 3D dynamic mesh coding. Image Vis. Comput. 26, 7 (2008), 1012--1026.Google Scholar
Digital Library
- Zhile Ren and Gregory Shakhnarovich. 2013. Image segmentation by cascaded region agglomeration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2011--2018.Google Scholar
Digital Library
- Mirko Sattler, Ralf Sarlette, and Reinhard Klein. 2005. Simple and efficient compression of animation sequences. In Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation. 209--217.Google Scholar
Digital Library
- Alex Smola, Arthur Gretton, Le Song, and Bernhard Schölkopf. 2007. A Hilbert space embedding for distributions. In Proceedings of the 18th International Conference on Algorithmic Learning Theory. Springer-Verlag, 13--31.Google Scholar
- Nikolce Stefanoski, Xiaoliang Liu, Patrick Klie, and Jorn Ostermann. 2007. Scalable linear predictive coding of time-consistent 3D mesh sequences. In Proceedings of the 3DTV Conference. 1--4.Google Scholar
Cross Ref
- Nikolče Stefanoski and Jörn Ostermann. 2010. SPC: Fast and efficient scalable predictive coding of animated meshes. In Comput. Graph. For., Vol. 29. Wiley Online Library, 101--116.Google Scholar
- Robert W. Sumner and Jovan Popovic. 2004. Deformation transfer for triangle meshes. In Proceedings of the International Conference on Computer Graphics and Interactive Techniques 23, 3 (2004), 399--405.Google Scholar
- Art Tevs, Alexander Berner, Michael Wand, Ivo Ihrke, Martin Bokeloh, Jens Kerber, and Hans-Peter Seidel. 2012. Animation cartography—Intrinsic reconstruction of shape and motion. ACM Trans. Graph. 31, 2 (Apr. 2012).Google Scholar
Digital Library
- Shoichi Tsuchie, Tikara Hosino, and Masatake Higashi. 2014. High-quality vertex clustering for surface mesh segmentation using Student-t mixture model. Comput.-aided Des. 46 (2014), 69--78.Google Scholar
- Steven Van Vaerenbergh. 2010. Kernel Methods for Nonlinear Identification, Equalization and Separation of Signals. Ph.D. Dissertation. University of Cantabria. Retrieved from https://github.com/steven2358/kmbox.Google Scholar
- Libor Váša and Guido Brunnett. 2013. Exploiting connectivity to improve the tangential part of geometry prediction. IEEE Trans. Vis. Comput. Graph. 19, 9 (2013), 1467--1475.Google Scholar
Digital Library
- Libor Váša, Stefano Marras, Kai Hormann, and Guido Brunnett. 2014. Compressing dynamic meshes with geometric Laplacians. Comput. Graph. For. 33, 2 (2014), 145--154.Google Scholar
Digital Library
- Libor Váša and Vaclav Skala. 2009. COBRA: Compression of the basis for PCA represented animations. Comput. Graph. For. 28, 6 (2009), 1529--1540.Google Scholar
- Libor Váša and Vaclav Skala. 2011. A perception correlated comparison method for dynamic meshes. IEEE Trans. Vis. Comput. Graph. 17, 2 (2011), 220--30.Google Scholar
Digital Library
- Daniel Vlasic, Ilya Baran, Wojciech Matusik, and Jovan Popovic. 2008. Articulated mesh animation from multi-view silhouettes. In Proceedings of the International Conference on Computer Graphics and Interactive Techniques 27, 3 (2008), 97.Google Scholar
Digital Library
- Pengjie Wang, Zhigeng Pan, Mingmin Zhang, Rynson W. H. Lau, and Haiyu Song. 2013. The alpha parallelogram predictor: A lossless compression method for motion capture data. Inf. Sci. 232 (2013), 1--10.Google Scholar
Digital Library
- Stefanie Wuhrer and Alan Brunton. 2010. Segmenting animated objects into near-rigid components. Vis. Comput. 26, 2 (2010), 147--155.Google Scholar
Digital Library
- Bailin Yang, Zhaoyi Jiang, Jiantao Shangguan, Frederick W. B. Li, Chao Song, Yibo Guo, and Mingliang Xu. 2018. Compressed dynamic mesh sequence for progressive streaming. Computer Animation and Virtual Worlds 30, 6 (2018).Google Scholar
- Bailin Yang, Luhong Zhang, W. B. Frederick Li, Xiaoheng Jiang, Zhigang Deng, Meng Wang, and Mingliang Xu. 2018. Motion-aware compression and transmission of mesh animation sequences. ACM Trans. Intell. Syst. Technol. 10, 3 (2018).Google Scholar
- Jeong Hyu Yang, Chang Su Kim, and Sang Uk Lee. 2002. Compression of 3-D triangle mesh sequences based on vertex-wise motion vector prediction. IEEE Trans. Circ. Syst. Video Technol. 12, 12 (2002), 1178--1184.Google Scholar
Digital Library
- Yazhou Yuan, Yu Zhang, Zhixin Liu, and Xinping Guan. 2017. Lossless coding scheme for data acquisition under limited communication bandwidth. Dig. Sig. Proc. 69 (2017), 204--211.Google Scholar
Digital Library
- Mingyang Zhu, Huaijiang Sun, and Zhigang Deng. 2012. Quaternion space sparse decomposition for motion compression and retrieval. In Proceedings of the 11th ACM SIGGRAPH/Eurographics Conference on Computer Animation. Eurographics Association, 183--192.Google Scholar
Digital Library
- Jacob Ziv and Abraham Lempel. 1977. A universal algorithm for sequential data compression. IEEE Trans. Inf. Theor. 23, 3 (1977), 337--343.Google Scholar
Digital Library
Index Terms
Spatio-temporal Segmentation Based Adaptive Compression of Dynamic Mesh Sequences
Recommendations
3D mesh animation compression based on adaptive spatio-temporal segmentation
I3D '19: Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and GamesWith the recent advances of data acquisition techniques, the compression of various 3D mesh animation data has become an important topic in computer graphics community. In this paper, we present a new spatio-temporal segmentation-based approach for the ...
3-D mesh sequence compression using wavelet-based multi-resolution analysis
In this paper, we present two compression methods for irregular three-dimensional (3-D) mesh sequences with constant connectivity. The proposed methods mainly use an exact integer spatial wavelet analysis (SWA) technique to efficiently decorrelate the ...
Semi-regular representation and progressive compression of 3-D dynamic mesh sequences
We propose an algorithm that represents three-dimensional dynamic objects with a semi-regular mesh sequence and compresses the sequence using the spatiotemporal wavelet transform. Given an irregular mesh sequence, we construct a semi-regular mesh ...






Comments