Template-Free 3D Reconstruction of Poorly-Textured Nonrigid Surfaces

详细信息    查看全文

• 关键词：Non ; rigid 3D reconstruction ; Poorly ; textured surfaces ; Template ; free shape estimation
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9911
• 期：1
• 页码：648-663
• 全文大小：3,724 KB
• 参考文献：1.Salzmann, M., Urtasun, R.: Beyond feature points: structured prediction for monocular non-rigid 3D reconstruction. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 245–259. Springer, Heidelberg (2012). doi:10.​1007/​978-3-642-33765-9_​18
  2.Ngo, T.D., Park, S., Jorstad, A.A., Crivellaro, A., Yoo, C., Fua, P.: Dense image registration and deformable surface reconstruction in presence of occlusions and minimal texture. In: ICCV (2015)
  3.Chhatkuli, A., Pizarro, D., Bartoli, A.: Stable template-based isometric 3D reconstruction in all imaging conditions by linear least-squares. In: CVPR (2014)
  4.Perriollat, M., Hartley, R., Bartoli, A.: Monocular template-based reconstruction of inextensible surfaces. Int. J. Comput. Vis. (IJCV) 95(2), 124–127 (2011)MathSciNet CrossRef MATH
  5.Salzmann, M., Urtasun, R., Fua, P.: Local deformation models for monocular 3D shape recovery. In: CVPR (2008)
  6.Bartoli, A., Gerard, Y., Chadebecq, F., Collins, T.: On template-based reconstruction from a single view: analytical solutions and proofs of well-posedness for developable, isometric and conformal surfaces. In: CVPR (2012)
  7.Bartoli, A., Collins, T.: Template-based isometric deformable 3D reconstruction with sampling-based focal length self-calibration. In: CVPR (2013)
  8.Bartoli, A., Pizarro, D., Collins, T.: A robust analytical solution to isometric shape-from-template with focal length calibration. In: ICCV (2013)
  9.Salzmann, M., Fua, P.: Reconstructing sharply folding surfaces: a convex formulation. In: CVPR (2009)
  10.Salzmann, M., Urtasun, R.: Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction. In: CVPR (2010)
  11.Yu, R., Russell, C., Campbell, N., Agapito, L.: Direct, dense, and deformable: template-based non-rigid 3D reconstruction from RGB video. In: ICCV (2015)
  12.Malti, A., Bartoli, A., Hartley, R.: A linear least-squares solution to elastic shape-from-template. In: CVPR (2015)
  13.Ngo, T.D., Östlund, J., Fua, P.: Template-based monocular 3D shape recovery using laplacian meshes. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 172–187 (2016)CrossRef
  14.Russell, C., Yu, R., Agapito, L.: Video-popup: Monocular 3D reconstruction of dynamic scenes. In: ECCV (2014)
  15.Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: CVPR (2000)
  16.Akhter, I., Sheikh, Y., Khan, S., Kanade, T.: Nonrigid structure from motion in trajectory space. In: NIPS (2008)
  17.Taylor, J., Jepson, A., Kutulakos, K.: Non-rigid structure from locally-rigid motion. In: CVPR (2010)
  18.Dai, Y., Li, H., He, M.: A simple prior-free method for nonrigid structure from motion factorization. In: CVPR (2012)
  19.Vicente, S., Agapito, L.: Soft inextensibility constraints for template-free non-rigid reconstruction. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 426–440. Springer, Heidelberg (2012). doi:10.​1007/​978-3-642-33712-3_​31
  20.Chhatkuliand, A., Pizarro, D., Bartoli, A.: Non-rigid shape-from-motion for isometric surfaces using infinitesimal planarity. In: BMVC (2014)
  21.Garg, R., Roussos, A., Agapito, L.: Dense variational reconstruction of non-rigid surfaces from monocular video. In: CVPR (2013)
  22.Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. (IJCV) 1(4), 321–331 (1988)CrossRef MATH
  23.Fua, P., Leclerc, Y.G.: Object-centered surface reconstruction: combining multi-image stereo and shading. Int. J. Comput. Vis. (IJCV) 16(1), 35–56 (1995)CrossRef
  24.Greminger, M., Nelson, B.: Deformable object tracking using the boundary element method. In: CVPR (2003)
  25.Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998). doi:10.​1007/​BFb0054760
  26.Matthews, I., Baker, S.: Active appearance models revisited. Int. J. Comput. Vis. (IJCV) 60(2), 135–164 (2004)CrossRef
  27.Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: SIGGRAPH (1999)
  28.Xiao, J., Baker, S., Matthews, I., Kanade, T.: Real-time combined 2D+3D active appearance models. In: CVPR (2004)
  29.Blanz, V., Basso, C., Poggio, T., Vetter, T.: Reanimating faces in images and video. In: Eurographics (2003)
  30.Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. Int. J. Comput. Vis. (IJCV) 9(2), 137–154 (1992)CrossRef
  31.Garg, R., Roussos, A., Agapito, L.: A variational approach to video registration with subspace constraints. Int. J. Comput. Vis. (IJCV) 104(3), 286–314 (2013)MathSciNet CrossRef MATH
  32.Woodford, O., Torr, P., Reid, I., Fitzgibbon, A.: Global stereo reconstruction under second order smoothness priors
  33.Lempitsky, V., Rother, C., Roth, S., Blake, A.: Fusion moves for markov random field optimization. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 32(8), 1392–1405 (2010)CrossRef
  34.Ishikawa, H.: Higher-order clique reduction in binary graph cut. In: CVPR (2009)
  35.Rother, C., Kolmogorov, V., Lempitsky, V., Szummer, M.: Optimizing binary MRFs via extended roof duality. In: CVPR (2007)
  36.Ishikawa, H.: Higher-order gradient descent by fusion-move graph cut. In: ICCV (2009)
  37. http://​cvlab.​epfl.​ch/​data/​dsr
  
• 作者单位：Xuan Wang (17)
  Mathieu Salzmann (18)
  Fei Wang (17)
  Jizhong Zhao (17)
  
  17. Xi’an Jiaotong University, Xi’an, China
  18. CVLab, EPFL, Zurich, Switzerland
  
• 丛书名：Computer Vision – ECCV 2016
• ISBN：978-3-319-46478-7
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9911

文摘

Two main classes of approaches have been studied to perform monocular nonrigid 3D reconstruction: Template-based methods and Non-rigid Structure from Motion techniques. While the first ones have been applied to reconstruct poorly-textured surfaces, they assume the availability of a 3D shape model prior to reconstruction. By contrast, the second ones do not require such a shape template, but, instead, rely on points being tracked throughout a video sequence, and are thus ill-suited to handle poorly-textured surfaces. In this paper, we introduce a template-free approach to reconstructing a poorly-textured, deformable surface. To this end, we leverage surface isometry and formulate 3D reconstruction as the joint problem of non-rigid image registration and depth estimation. Our experiments demonstrate that our approach yields much more accurate 3D reconstructions than state-of-the-art techniques.