Abstract
We present the first end-to-end solution to create high-quality free-viewpoint video encoded as a compact data stream. Our system records performances using a dense set of RGB and IR video cameras, generates dynamic textured surfaces, and compresses these to a streamable 3D video format. Four technical advances contribute to high fidelity and robustness: multimodal multi-view stereo fusing RGB, IR, and silhouette information; adaptive meshing guided by automatic detection of perceptually salient areas; mesh tracking to create temporally coherent subsequences; and encoding of tracked textured meshes as an MPEG video stream. Quantitative experiments demonstrate geometric accuracy, texture fidelity, and encoding efficiency. We release several datasets with calibrated inputs and processed results to foster future research.
Supplemental Material
Available for Download
Supplemental files
- 4D View Solutions, 2007. http://www.4dviews.com.Google Scholar
- Ahmed, N., Theobalt, C., Dobrev, P., and Seidel, H. 2008. Robust fusion of dynamic shape and normal capture for high-quality reconstruction of time-varying geometry. In Proc. CVPR.Google Scholar
- Ahmed, N., Theobalt, C., Rossl, C., Thrun, S., and Seidel, H. 2008. Dense correspondence finding for parameterization-free animation reconstruction from video. In Proc. CVPR.Google Scholar
- Alexa, M., Behr, J., Cohen-Or, D., Fleishman, S., Levin, D., and Silva, C. T. 2001. Point set surfaces. In Proc. Conf. on Visualization. Google ScholarDigital Library
- Aspert, N., Santa-cruz, D., and Ebrahimi, T. 2002. MESH: Measuring errors between surfaces using the Hausdorff distance. In Proc. ICME.Google Scholar
- Bleyer, M., Rhemann, C., and Rother, C. 2011. PatchMatch stereo - stereo matching with slanted support windows. In Proc. BMVC.Google Scholar
- Bojsen-Hansen, M., Li, H., and Wojtan, C. 2012. Tracking surfaces with evolving topology. ACM Trans. Graph. 31, 4. Google ScholarDigital Library
- Borshukov, G., Piponi, D., Larsen, O., Lewis, J. P., and Tempelaar-Lietz, C. 2005. Universal capture -- Image-based facial animation for "The Matrix Reloaded". In ACM SIGGRAPH Courses. Google ScholarDigital Library
- Budd, C., Huang, P., Klaudiny, M., and Hilton, A. 2013. Global non-rigid alignment of surface sequences. Int. J. Comput. Vision 102, 1--3. Google ScholarDigital Library
- Campbell, N. D. F., Vogiatzis, G., Hernandez, C., and Cipolla, R. 2008. Using multiple hypotheses to improve depth-maps for multi-view stereo. In Proc. ECCV. Google ScholarDigital Library
- Carranza, J., Theobalt, C., Magnor, M. A., and Seidel, H.-P. 2003. Free-viewpoint video of human actors. ACM Trans. Graph. 22, 3. Google ScholarDigital Library
- Casas, D., Volino, M., Collomosse, J., and Hilton, A. 2014. 4D video textures for interactive character appearance. Comput. Graph. Forum 33, 2. Google ScholarDigital Library
- Chuang, M., Luo, L., Brown, B., Rusinkiewicz, S., and Kazhdan, M. 2009. Estimating the Laplace-Beltrami operator by restricting 3D functions. Symposium on Geometry Processing. Google ScholarDigital Library
- de Aguiar, E., Stoll, C., Theobalt, C., Ahmed, N., Seidel, H.-P., and Thrun, S. 2008. Performance capture from sparse multi-view video. ACM Trans. Graph. 27, 3. Google ScholarDigital Library
- DoubleMe, 2014. https://www.doubleme.me.Google Scholar
- Erickson, J., and Whittlesey, K. 2005. Greedy optimal homotopy and homology generators. In Proc. ACM-SIAM Symposium on Discrete algorithms. Google ScholarDigital Library
- Franco, J., Lapierre, M., and Boyer, E. 2006. Visual shapes of silhouette sets. In Proc. Intl. Symp. 3D Data Processing, Visualization and Transmission. Google ScholarDigital Library
- FreeD, 2014. http://replay-technologies.com.Google Scholar
- Furukawa, Y., and Ponce, J. 2010. Accurate, dense, and robust multiview stereopsis. IEEE PAMI 32, 8. Google ScholarDigital Library
- Gal, R., Wexler, Y., Ofek, E., Hoppe, H., and Cohen-Or, D. 2010. Seamless montage for texturing models. Comput. Graph. Forum 29, 2.Google ScholarCross Ref
- Gall, J., Stoll, C., Aguiar, E. D., Theobalt, C., Rosenhahn, B., and peter Seidel, H. 2009. Motion capture using joint skeleton tracking and surface estimation. In Proc. CVPR.Google ScholarCross Ref
- Garland, M., and Heckbert, P. S. 1997. Surface simplification using quadric error metrics. In ACM SIGGRAPH. Google ScholarDigital Library
- Goesele, M., Curless, B., and Seitz, S. M. 2006. Multi-view stereo revisited. In Proc. CVPR. Google ScholarDigital Library
- Goldluecke, B., and Magnor, M. 2004. Space-time isosurface evolution for temporally coherent 3D reconstruction. In Proc. CVPR.Google Scholar
- Golomb, S. 1966. Run-length encodings (corresp.). IEEE Transactions on Information Theory 12, 3. Google ScholarDigital Library
- Guennebaud, G., Jacob, B., et al., 2010. Eigen v3. http://eigen.tuxfamily.org.Google Scholar
- Guskov, I., and Wood, Z. J. 2001. Topological noise removal. In Proc. Graphics Interface. Google ScholarDigital Library
- Hernandez, C., and Schmitt, F. 2004. Silhouette and stereo fusion for 3D object modeling. Computer Vision and Image Understanding 96, 3. Google ScholarDigital Library
- Hiep, V. H., Keriven, R., Labatut, P., and Pons, J.-P. 2009. Towards high-resolution large-scale multi-view stereo. In Proc. CVPR.Google Scholar
- Hu, X., and Mordohai, P. 2012. A quantitative evaluation of confidence measures for stereo vision. IEEE PAMI 34, 11. Google ScholarDigital Library
- Huang, C.-H., Boyer, E., Navab, N., and Ilic, S. 2014. Human shape and pose tracking using keyframes. In Proc. CVPR. Google ScholarDigital Library
- ISO/IEC 23009-1, 2014. Information technology -- dynamic adaptive streaming over HTTP (DASH) -- Part 1: Media presentation description and segment formats.Google Scholar
- Kanade, T., Rander, P., and Narayanan, P. J. 1997. Virtualized reality: Constructing virtual worlds from real scenes. IEEE Multimedia 4, 1. Google ScholarDigital Library
- Kazhdan, M., and Hoppe, H. 2013. Screened Poisson surface reconstruction. ACM Trans. Graph. 32, 3. Google ScholarDigital Library
- Kazhdan, M., Bolitho, M., and Hoppe, H. 2006. Poisson surface reconstruction. In Symposium on Geometry Processing. Google ScholarDigital Library
- Klaudiny, M., Budd, C., and Hilton, A. 2012. Towards optimal non-rigid surface tracking. In Proc. ECCV. Google ScholarDigital Library
- Labatut, P., Pons, J.-P., and Keriven, R. 2007. Efficient multi-view reconstruction of large-scale scenes using interest points, delaunay triangulation and graph cuts. In Proc. ICCV.Google Scholar
- Lee, C. H., Varshney, A., and Jacobs, D. W. 2005. Mesh saliency. ACM Trans. Graph. 24, 3. Google ScholarDigital Library
- Lempitsky, V. S., and Ivanov, D. V. 2007. Seamless mosaicing of image-based texture maps. In Proc. CVPR.Google Scholar
- Letouzey, A., and Boyer, E. 2012. Progressive shape models. In Proc. CVPR. Google ScholarDigital Library
- Li, H., Adams, B., Guibas, L. J., and Pauly, M. 2009. Robust single-view geometry and motion reconstruction. ACM Trans. Graph. 28, 5. Google ScholarDigital Library
- Lindstrom, P., and Turk, G. 2000. Image-driven simplification. ACM Trans. Graph. 19, 3. Google ScholarDigital Library
- Liu, Y., Dai, Q., and Xu, W. 2010. A point-cloud-based multiview stereo algorithm for free-viewpoint video. IEEE TVCG. Google ScholarDigital Library
- Matusik, W., Buehler, C., Raskar, R., Gortler, S. J., and McMillan, L. 2000. Image-based visual hulls. In ACM SIGGRAPH. Google ScholarDigital Library
- Microsoft, 2011. UVAtlas. http://uvatlas.codeplex.com.Google Scholar
- Moezzi, S., Tai, L.-C., and Gerard, P. 1997. Virtual view generation for 3D digital video. IEEE Multimedia 4, 1. Google ScholarDigital Library
- Narayanan, P., Rander, P., and Kanade, T. 1998. Constructing virtual worlds using dense stereo. In Proc. ICCV. Google ScholarDigital Library
- Shan, Q., Curless, B., Furukawa, Y., Hernandez, C., and Seitz, S. M. 2014. Occluding contours for multi-view stereo. In Proc. ECCV.Google Scholar
- Sinha, S. N., and Pollefeys, M. 2005. Multi-view reconstruction using photo-consistency and exact silhouette constraints: a maximum-flow formulation. In Proc. ICCV. Google ScholarDigital Library
- Song, P., Wu, X., and Wang, M. Y. 2010. Volumetric stereo and silhouette fusion for image-based modeling. The Visual Computer 26, 12. Google ScholarDigital Library
- Starck, J., and Hilton, A. 2007. Surface capture for performance-based animation. IEEE Computer Graphics and Application 27, 6. Google ScholarDigital Library
- Sumner, R. W., Schmid, J., and Pauly, M. 2007. Embedded deformation for shape manipulation. ACM Trans. Graph. 26, 3. Google ScholarDigital Library
- Vasa, L., and Skala, V. 2007. CoDDyaC: Connectivity Driven Dynamic Mesh Compression. In Proc. 3DTV.Google Scholar
- Vlasic, D., Baran, I., Matusik, W., and Popovic, J. 2008. Articulated mesh animation from multiview silhouettes. ACM Trans. Graph. 27, 3. Google ScholarDigital Library
- Vlasic, D., Peers, P., Baran, I., Debevec, P., Popović, J., Rusinkiewicz, S., and Matusik, W. 2009. Dynamic shape capture using multi-view photometric stereo. ACM Trans. Graph. 28, 5. Google ScholarDigital Library
- Volino, M., Casas, D., Collomosse, J. P., and Hilton, A. 2014. Optimal representation of multiple view video. In Proc. BMVC.Google Scholar
- Wand, M., Adams, B., Ovsjanikov, M., Berner, A., Bokeloh, M., Jenke, P., Guibas, L., Seidel, H.-P., and Schilling, A. 2009. Efficient reconstruction of nonrigid shape and motion from real-time 3D scanner data. ACM Trans. Graph. 28, 2. Google ScholarDigital Library
- Wang, Z., Bovik, A. C., Sheikh, H. R., and Simoncelli, E. P. 2004. Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Proc. 13, 4. Google ScholarDigital Library
- Wood, Z., Hoppe, H., Desbrun, M., and Schröder, P. 2004. Removing excess topology from isosurfaces. ACM Trans. Graph. 23, 2. Google ScholarDigital Library
- Wu, C., Varanasi, K., Liu, Y., Seidel, H.-P., and Theobalt, C. 2011. Shading--based dynamic shape refinement from multi-view video under general illumination. In Proc. ICCV. Google ScholarDigital Library
- Ye, G., Liu, Y., Deng, Y., Hasler, N., Ji, X., Dai, Q., and Theobalt, C. 2013. Free-viewpoint video of human actors using multiple handheld Kinects. IEEE Trans. on System, Man & Cybernetics 43, 5.Google Scholar
- Yu, F., Luo, H., Lu, Z., and Wang, P. 2010. 3D mesh compression. Three-Dimensional Model Analysis and Processing.Google Scholar
- Zhou, Q.-Y., and Koltun, V. 2014. Color map optimization for 3D reconstruction with consumer depth cameras. ACM Trans. Graph. 33, 4. Google ScholarDigital Library
- Zitnick, C. L., Kang, S. B., Uyttendaele, M., Winder, S., and Szeliski, R. 2004. High-quality video view interpolation using a layered representation. ACM Trans. Graph. 23, 3. Google ScholarDigital Library
- Zollhöfer, M., Niessner, M., Izadi, S., Rehmann, C., Zach, C., Fisher, M., Wu, C., Fitzgibbon, A., Loop, C., Theobalt, C., and Stamminger, M. 2014. Real-time non-rigid reconstruction using an RGB-D camera. ACM Trans. Graph. 33, 4. Google ScholarDigital Library
Index Terms
- High-quality streamable free-viewpoint video
Recommendations
Photometric Bundle Adjustment for Dense Multi-view 3D Modeling
CVPR '14: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern RecognitionMotivated by a Bayesian vision of the 3D multi-view reconstruction from images problem, we propose a dense 3D reconstruction technique that jointly refines the shape and the camera parameters of a scene by minimizing the photometric reprojection error ...
Stereo fusion
A stereo fusion system that combines binocular and refractive stereo is presented.Our stereo fusion outperforms traditional binocular and refractive stereo.An efficient calibration method for refractive stereo is proposed. Display Omitted The ...
Free Viewpoint Video Coding With Rate-Distortion Analysis
To improve free viewpoint video (FVV) coding efficiency and optimize the quality of the synthesized virtual view video, this paper proposes a depth-assisted FVV coding framework and analyzes the rate-distortion (R-D) property of the synthesized virtual ...
Comments