iccv iccv2013 iccv2013-128 iccv2013-128-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ali Osman Ulusoy, Octavian Biris, Joseph L. Mundy
Abstract: This paper presents a probabilistic volumetric framework for image based modeling of general dynamic 3-d scenes. The framework is targeted towards high quality modeling of complex scenes evolving over thousands of frames. Extensive storage and computational resources are required in processing large scale space-time (4-d) data. Existing methods typically store separate 3-d models at each time step and do not address such limitations. A novel 4-d representation is proposed that adaptively subdivides in space and time to explain the appearance of 3-d dynamic surfaces. This representation is shown to achieve compression of 4-d data and provide efficient spatio-temporal processing. The advances oftheproposedframework is demonstrated on standard datasets using free-viewpoint video and 3-d tracking applications.
[1] 4-d repository. http : / / 4 drepo s it ory . inrialpe s . fr/, 2012. 2, 5
[2] Vxl. http : / / http : / / s ource fo rge . net / pro j e ct s /vxl /, 2012. 5
[3] M. Agrawal and L. Davis. A probabilistic framework for surface reconstruction from multiple images. CVPR, 2001 .
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11] 3, 4 E. D. Aguiar, C. Stoll, and C. Theobalt. Performance capture from sparse multi-view video. ACM SIGGRAPH, 2008. 2 R. Bhotika, D. J. Fleet, and K. N. Kutulakos. A Probabilistic Theory of Occupancy and Emptiness. In ECCV, 2002. 3 J. D. Bonet and P. Viola. Poxels: Probabilistic voxelized volume reconstruction. ICCV, 1999. 3, 4 C. Budd, P. Huang, M. Klaudiny, and A. Hilton. Global Nonrigid Alignment of Surface Sequences. IJCV, 2012. 2 C. Cagniart, E. Boyer, and S. Ilic. Free-form mesh tracking: A patch-based approach. CVPR, 2010. 2 C. Cagniart, E. Boyer, and S. Ilic. Probabilistic Deformable Surface Tracking. ECCV, 2010. 2 R. L. Carceroni and K. N. Kutalakos. Multi-view scene capture by surfel sampling: from video streams to non-rigid 3D motion, shape and reflectance. ICCV, 2001 . 2 J. Carranza, C. Theobalt, M. a. Magnor, and H.-P. Seidel. Free-viewpoint video of human actors. ACM TOG, 2003. 2, 4
[12] D. Crispell, J. Mundy, and G. Taubin. A Variable-Resolution Probabilistic Three-Dimensional Model for Change Detection. IEEE Transactions on Geoscience and Remote Sensing, 2012. 4
[13] P. Debevec, C. Taylor, and J. Malik. Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach. ACM SIGGRAPH, 1996. 4 512
[14] J. Deutscher, a. Blake, and I. Reid. Articulated body motion capture by annealed particle filtering. CVPR, 2000. 7
[15] Y. Furukawa and J. Ponce. Dense 3d motion capture from synchronized video streams. CVPR, 2008. 2
[16] L. Guan, J. Franco, and M. Pollefeys. 3d occlusion inference
[17]
[18]
[19]
[20]
[21]
[22]
[23]
[24]
[25]
[26]
[27]
[28] from silhouette cues. CVPR, 2007. 3 L. Guan and M. Pollefeys. Probabilistic 3D Occupancy Flow with Latent Silhouette Cues. CVPR, 2010. 1, 2, 7 N. Hasler and B. Rosenhahn. Markerless motion capture with unsynchronized moving cameras. CVPR, 2009. 8 a. Letouzey and E. Boyer. Progressive shape models. CVPR, 2012. 2 K.-L. MA. Visualizing Time-varying Volume Data. Computing in Science and Engineering, March 2003. 2 A. Miller, V. Jain, and J. L. Mundy. Real-time rendering and dynamic updating of 3-d volumetric data. In Proceedings of the Fourth Workshop on GPGPU, 2011. 2, 3 T. Pollard and J. L. Mundy. Change Detection in a 3-d World. In CVPR, June 2007. 3, 4, 5 T. Popham. Tracking 3D Surfaces Using Multiple Cameras : A Probabilistic Approach by. PhD thesis, University of Warwick, 2010. 2 A. Prock and C. Dyer. Towards real-time voxel coloring. Proceedings of the DARPA Image Understanding Workshop, 1998. 1, 2 M. I. Restrepo, B. Mayer, A. O. Ulusoy, and J. L. Mundy. Characterization of 3-d Volumetric Probabilistic Scenes for Object Recognition. Journal of Selected Topics in Signal Processing, 2012. 7 H.-W. Shen, L.-J. Chiang, and K.-L. Ma. A fast volume rendering algorithm for time-varying fields using a time-space partitioning (TSP) tree. In IEEE Proceedings Visualization, 1999. 2, 3 G. Slabaugh, R. Schafer, and M. Hans. Image-based photo hulls. 3DPVT, 2002. 4 T. Popa and I. South-Dickinson and D. Bradley and A. Sheffer and W. Heidrich. Globally Consistent Space-Time Re-
[29]
[30]
[31]
[32]
[33]
[34] construction. Computer Graphics Forum, 2010. 2 A. Taneja, L. Ballan, and M. Pollefeys. Image based detection of geometric changes in urban environments. In ICCV, 2011. 2 A. Taneja, L. Ballan, and M. Pollefeys. Modeling dynamic scenes recorded with freely moving cameras. ACCV, 2011. 2, 8 K. Varanasi and A. Zaharescu. Temporal surface tracking using mesh evolution. ECCV, 2008. 2 S. Vedula. Image Based Spatio-Temporal Modeling and View Interpolation of Dynamic Events. PhD thesis, 2001. 1, 2, 7 Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. Image quality assessment: From error visibility to structural similarity. ICIP, 2004. 5 S. W ¨urmlin, E. Lamboray, and M. Gross. 3D video fragments: dynamic point samples for real-time free-viewpoint video. Computers & Graphics, 2004. 2