ABSTRACT
Dynamic shape capture from casual videos is a fundamental task at the cross-fertilization of Computer Vision and Computer Graphics. Notwithstanding, recent advances in low-cost dynamic scanners turn the cross parametrization of non-rigid animatable surface into an ill-posed and vision-oriented problem. In this paper, we propose a cage-based technique to register non-rigid observed shapes using a meaningful, reduced and animator-friendly embedding. This subspace offers natural silhouette-awareness to encode the deformation complexity already encapsulated in the targets. The estimated time-varying parameters associated the underlying flexible structure allows potential reuse. In particular, we leverage the problem of highly non-rigid spacetime registration by employing an elastoplastic coarse cage. Thus, we perform scalable handle-aware biharmonic shape registration, relying on the high-level of shape abstraction offered by this space-based paradigm. Finally, we tested the effectiveness of our proposed solution on real-world datasets capturing time-varying multi-view silhouettes.
- Zheng, Q., Sharf, A., Tagliasacchi, A., Chen, B., Zhang, H., Sheffer, A., and Cohen-Or, D.: Consensus skeleton for non-rigid space-time registration. Computer Graphics Forum 29, 2. (2010)Google Scholar
- Xian, C., Lin, H., and Gao, S.: Automatic cage generation by improved obbs for mesh deformation. In Vis. Comput. (2012) Google ScholarDigital Library
- Ju, T., Zhou, Q-Y., Van de Panne, M., Cohen-Or, D. and Neumann, U.: Reusable skinning templates using cage-based deformations. In ACM Trans. Graph. (2008) Google ScholarDigital Library
- Ju, T., Schaefer, S. and Warren, J.: Mean value coordinates for closed triangular meshes. In ACM Trans. Graph. (2005) Google ScholarDigital Library
- Lipman, Y., Kopf, J., Cohen-Or, D., and Levin, D.: GPU-assisted positive mean value coordinates for mesh deformations. In SGP. (2007) Google ScholarDigital Library
- Lipman, Y., Levin, D., and Cohen-Or D.: Green Coordinates. In ACM Trans. Graph. (2008) Google ScholarDigital Library
- Joshi, P., Meyer, M., DeRose, T., Green, B., and Sanocki, T.: Harmonic coordinates for character articulation. In ACM Trans. Graph. (2007) Google ScholarDigital Library
- Ben-Chen, M., Weber, O., and Gotsman, C.: Variational harmonic maps for space deformation. In ACM Trans. Graph. (2009) Google ScholarDigital Library
- Weber O., Poranne R., and Gotsman, C.: Spatial deformation transfer, In Computer Graphics Forum. (2012)Google Scholar
- Jacobson, A., Baran, I., Popović, J. and Sorkine, O.: Bounded Biharmonic Weights for Real-Time Deformation. In ACM Trans. Graph. (2011) Google ScholarDigital Library
- Chen, L., Huang, J., Sun, H., and Bao, H.: Cage-based deformation transfer. In Comput. Graph. (2010) Google ScholarDigital Library
- Ben-Chen, M., Weber, O., and Gotsman, C.: Spatial deformation transfer, In SCA. (2009) Google ScholarDigital Library
- Chang, W., and Zwicker, M.: Global Registration of Dynamic Range Scans for Articulated Model Reconstruction, In ACM Trans. Graph. (2011) Google ScholarDigital Library
- de Aguiar, E., Stoll, C., Theobalt, C., Ahmed, N., Seidel, H-P., and Thrun, S.: Performance capture from sparse multi-view video. In SIGGRAPH'08. (2008) Google ScholarDigital Library
- Ballan, L., and Cortelazzo, G. M.: Marker-less motion capture of skinned models in a four camera set-up using optical flow and silhouettes. In 3DPVT. (2008)Google Scholar
- Amberg, B., Romdhani, S., and Vetter, T.: Optimal Step Nonrigid ICP Algorithms for Surface Registration. In CVPR. (2007)Google Scholar
- Gall, J., Stoll, C., de Aguiar, E., Theobalt, C., Rosenhahn, B., and Seidel, H.-P.: Motion Capture Using Joint Skeleton Tracking and Surface Estimation. In CVPR. (2009)Google Scholar
- Budd, C., Huang, P., and Hilton, A.: Hierarchical Shape Matching for Temporally Consistent 3D Video. In 3DIMPVT. (2011) Google ScholarDigital Library
- Guennebaud, G., and Gross, M.: Algebraic point set surfaces. In ACM Trans. Graph. (2007) Google ScholarDigital Library
- Besl, P., and McKay, N.: A Method for Registration of 3-D Shapes. In TPAMI. (1992) Google ScholarDigital Library
- Chang, W., and Zwicker, M.: Automatic Registration for Articulated Shapes. In SGP. (2008) Google ScholarDigital Library
- Connor, M., and Kumar, P.: Fast Construction of k-Nearest Neighbor Graphs for Point Clouds. In TGCV. (2010) Google ScholarDigital Library
- Hornung, A., and Kobbelt, L.: Robust reconstruction of watertight 3D models from non-uniformly sampled point clouds without normal information. In SGP. (2006) Google ScholarDigital Library
- Huang, P., Budd, C., and Hilton, A.: Global temporal registration of multiple non-rigid surface sequences. In CVPR. (2011)Google Scholar
- Huang, Q-X., Adams, B., Wicke, M., and Guibas, L.: Non-Rigid Registration Under Isometric Deformations. In Comput. Graph. Forum. (2008) Google ScholarDigital Library
- Laurentini, A.: The Visual Hull Concept for Silhouette-Based Image Understanding. In IEEE TPAMI. (1994) Google ScholarDigital Library
- Kim, K., Sakamoto, R., Kitahara, I., Toriyama, T., and Kogure, K.: Robust Foreground Segmentation from Color Video Sequences Using Background Subtraction with Multiple Thresholds. In Third Korea-Japan Joint Workshop on Pattern Recognition. (2006)Google Scholar
- Starck, J., and Hilton, A.: Surface Capture for Performance-Based Animation. In IEEE Comput. Graph. Appl. (2007) Google ScholarDigital Library
- Li, H., Sumner, R., and Pauly, M.: Global Correspondence Optimization for Non-Rigid Registration of Depth Scans, In SGP. (2008) Google ScholarDigital Library
- Li, H., Adams, B., Guibas, L., and Pauly, M.: Robust Single-View Geometry And Motion Reconstruction. In ACM Trans. on Graph. (2009) Google ScholarDigital Library
- Li, H., Luo, L., Vlasic, D., Peers, P., Popović, J., Pauly, M., and Rusinkiewicz, S.: Temporally Coherent Completion of Dynamic Shapes. In ACM Trans. Graph. (2012) Google ScholarDigital Library
- Grauman, K., Shakhnarovich, G., and Darrell, T.: A bayesian approach to image-based visual hull reconstruction. In CVPR. (2003) Google ScholarDigital Library
- Kolev, K., Brox, T., and Cremers, D.: Fast Joint Estimation of Silhouettes and Dense 3D Geometry from Multiple Images. In IEEE TPAMI. (2012) Google ScholarDigital Library
- Matusik, W., Buehler, C., and McMillan, L.: Polyhedral Visual Hulls for Real-Time Rendering. In Eurographics Workshop on Rendering Techniques. (2001) Google ScholarDigital Library
- Corazza, S., Mündermann, L., Gambaretto, E., Ferrigno, G., and Andriacchi, T.: Markerless Motion Capture through Visual Hull, Articulated ICP and Subject Specific Model Generation, In Int. J. Comput. Vision. (2010) Google ScholarDigital Library
- Liu, Y., Stoll, C., Gall, J., Seidel, H.-P. and Theobalt, C.: Markerless motion capture of interacting characters using multi-view image segmentation In CVPR. (2011)Google Scholar
- Budd, C., and Hilton, A.: Temporal Alignment of 3D Video Sequences Using Shape and Appearance. 9th Conference on Visual Media Production (CVMP). (2010) Google ScholarDigital Library
- Botsch, M., and Sorkine, O.: On Linear Variational Surface Deformation Methods. In TVCG. (2008) Google ScholarDigital Library
- Desbrun, M., and Meyer, M., Schröder, P., and Barr, A.: Implicit fairing of irregular meshes using diffusion and curvature flow In SIGGRAPH'99. (1999) Google ScholarDigital Library
- Wald, I., Boulos, S., and Shirley, P.: Ray tracing deformable scenes using dynamic bounding volume hierarchies. In ACM Trans. Graph. (2007) Google ScholarDigital Library
- Popa, T. South-Dickinson, I., Bradley D., Sheffer A., and Heidrich, W.: Globally Consistent Space-Time Reconstruction. In SGP. (2010)Google Scholar
- Süssmuth, J., Zollhöfer, M., and Greiner, G.: Animation transplantation. In Comput. Animat. Virtual Worlds. (2010) Google ScholarDigital Library
- Münch, D., and Combès, B., and Prima, S.: A modified ICP algorithm for normal-guided surface registration. In Proceedings of SPIE 7623. (2010)Google Scholar
- Sagawa, R., Akasaka, K., Yagi, Y., Ha, H., and Van Gool, L.: Elastic Convolved ICP for the Registration of Deformable Objects. In 3DIM. (2009)Google Scholar
- Zheng, Q., Sharf, A., Tagliasacchi, A., Chen, B., Zhang, H., Sheffer, A., and Cohen-Or, D.: Consensus Skeleton for Non-Rigid Space-Time Registration. In Computer Graphics Forum. (2010)Google Scholar
- Tevs, A., Berner, A., Wand, M., Ihrke, I., Bokeloh, M., Kerber, J., and Seidel, H.-P.: Animation cartography: intrinsic reconstruction of shape and motion. In ACM Trans. Graph., (2012). Google ScholarDigital Library
- Liu, Y., Dai, Q., and Xu, W.: A Point-Cloud-Based Multi-view Stereo Algorithm for Free-Viewpoint Video. In TVCG. (2010) Google ScholarDigital Library
- Sharf, A., Alcantara, D., Lewiner, T., Greif, C., Sheffer, A., Amenta, N. and Cohen-Or, D.: Space-time surface reconstruction using incompressible flow. In ACM Trans. Graph. (2008) Google ScholarDigital Library
- Stoll, C., Karni, Z., Rossl, C., Yamauchi, H., and Seidel, H.-P.: Template Deformation for Point Cloud Fitting. In SPBG. (2006) Google ScholarDigital Library
- Tong, J., Zhou, J., Liu, L., Pan Z., and Yan, H.: Scanning 3D Full Human Bodies using Kinects. In TVCG. (2012) Google ScholarDigital Library
- Vogiatzis, G., Torr, P., and Cipolla, R.: Multi-View Stereo via Volumetric Graph-Cuts. In CVPR. (2005) Google ScholarDigital Library
- Wald, I.: On fast Construction of SAH-based Bounding Volume Hierarchies. In Proceedings of the IEEE Symposium on Interactive Ray Tracing. (2007) Google ScholarDigital Library
- Au, O., Fu, H., Tai, C.-T., and Cohen-Or, D.: Handle-aware isolines for scalable shape editing. In ACM Trans. Graphic. (2007) Google ScholarDigital Library
- Vlasic, D., Baran, I., Matusik, W., and Popović, J.: Articulated mesh animation from multi-view silhouettes. In ACM Trans. Graph. (2008) Google ScholarDigital Library
- Wand, M., Jenke, P., Huang, Q.-X., Bokeloh, M., Guibas, L., and Schilling, A.: Reconstruction of deforming geometry from time-varying point clouds. In SGP. (2007) Google ScholarDigital Library
- Yeh I.-C, Lin, C.-H., Sorkine, O., and Lee, T.-Y.: Template-based 3D Model Fitting Using Dual-domain Relaxation. In IEEE TVCG. (2010) Google ScholarDigital Library
- Witkin, A., and Kass, M.: Spacetime constraints. In SIGGRAPH. (1988) Google ScholarDigital Library
- Luo, W., Yamasaki, T., and Aizawa, K.: Articulated Human Motion Capture from. Segmented Visual Hulls and Surface Reconstruction. In APSIPA. (2010)Google Scholar
- Windheuser, T., Schlickewei, U., Schmidt, F., and Cremers, D.: Large-Scale Integer Linear Programming for Orientation-Preserving 3D Shape Matching. In SGP. (2011)Google Scholar
- Huang, P., Budd, C., and Hilton, A.: Global temporal registration of multiple non-rigid surface sequences. In CVPR. (2011)Google Scholar
- Jacobson, A., Baran, I., Popović, J., and Sorkine, O.: Bounded Biharmonic Weights for Real-Time Deformation. In ACM Trans. Graph. (2011) Google ScholarDigital Library
- Arya, S., Mount, D., Netanyahu, N., Silverman, R., and Wu, A.: An optimal algorithm for approximate nearest neighbor searching fixed dimensions. In J. ACM. (1998) Google ScholarDigital Library
Index Terms
- Iterative cage-based registration from multi-view silhouettes
Recommendations
Iterative cage-based registration for dynamic shape capture
SIGGRAPH '12: ACM SIGGRAPH 2012 PostersRecent advances in low-cost dynamic scanning turn the cross-parametrization of non-rigid animatable surface into a vision-oriented ill-posed problem. In contrast with [Li et al. 2012], we propose a novel detail-preserving registration approach with ...
Cage-based performance capture
SIGGRAPH '18: ACM SIGGRAPH 2018 CoursesNowadays, highly-detailed animations of live-actor performances are increasingly easier to acquire, and 3D Video has reached considerable attention in visual media productions. This lecture will address new paradigm to achieve performance capture using ...
Cage-based performance capture
SA '16: SIGGRAPH ASIA 2016 CoursesNowadays, highly-detailed animations of live-like performances are easier to acquire thanks to low-cost sensors. Also, 4D meshes have reached considerable attentions in visual media productions. This course will address new paradigm to achieve ...
Comments