Journal of Computing Science and Engineering

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Terrain Geometry from Monocular Image Sequences

  • Published : 2008.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Terrain reconstruction from images is an ill-posed, yet commonly desired Structure from Motion task when compositing visual effects into live-action photography. These surfaces are required for choreography of a scene, casting physically accurate shadows of CG elements, and occlusions. We present a novel framework for generating the geometry of landscapes from extremely noisy point cloud datasets obtained via limited resolution techniques, particularly optical flow based vision algorithms applied to live-action video plates. Our contribution is a new statistical approach to remove erroneous tracks ('outliers') by employing a unique combination of well established techniques-including Gaussian Mixture Models (GMMs) for robust parameter estimation and Radial Basis Functions (REFs) for scattered data interpolation-to exploit the natural constraints of this problem. Our algorithm offsets the tremendously laborious task of modeling these landscapes by hand, automatically generating a visually consistent, camera position dependent, thin-shell surface mesh within seconds for a typical tracking shot.

Keywords

References

  1. 2D3. Boujou 4. http://www.2d3.com.
  2. AMENTA, N., CHOI, S., AND KOLLURI, R. 2001. The Power Crust, Unions of Balls, and the Medial Axis Transform. In Computational Geometry: Theory and Applications. 127-153. https://doi.org/10.1016/S0925-7721(01)00017-7
  3. BARRON, J. L., FLEET, D. J., AND BEAUCHEMIN, S. 1994. Performance of optical flow techniques. In International Journal of Computer Vision. 43-77. https://doi.org/10.1007/BF01420984
  4. BOUMAN, C. A. 2005. Cluster: An Unsupervised Algorithm for Modeling Gaussian Mixtures. Tech. rep., Purdue.
  5. CARR, J. C., BEATSON, R. K., CHERRIE, J. B., MITCHELL, T. J., FRIGHT, W. R., MCCALLUM, B. C., AND EVANS, T. R. 2001. Reconstruction and Representation of 3D Objects with Radial Basis Functions. In ACM Siggraph. 67-76.
  6. CAZALS, F. AND GIESEN, J. 2004. Delaunay Triangulation Based Surface Reconstruction: Ideas and Algorithms. Tech. rep., INRIA Sophia-Antipoles.
  7. Fitzgibbon, A. W. and ZISSERMAN, A. 1998. Automatic Camera Recovery for Closed or Open Image Sequences. In European Conference on Computer Vision. 311-326.
  8. FORSYTH, D. A. AND PONCE, J. 2003. Computer Vision, a modern approach. Prentice Hall.
  9. HARTLEY, R. I. AND ZISSERMAN, A. 2004. Multiple View Geometry in Computer Vision. Cambridge University Press.
  10. HOPPE, H., DEROSE, T., DUCHAMP, T., MCDONALD, J., AND STUETZLE, W. 1992. Surface Reconstruction from Unorganized Points, Computer Graphics 26.
  11. HORNUNG, A. AND KOBBELT, L. 2006. Robust Reconstruction of Watertight 3D Models from Non-uniformly Sampled Point Clouds Without Normal Information. In Symposium on Geometry Processing. 41-50.
  12. ISENBURG, M., LIU, Y., SHEWCHUK, J., AND SNOEYINK, J. 2006. Streaming Computation of Delaunay Triangulations. In ACM Siggraph. 1049-1056.
  13. KAZHDAN, M., BOLITHO, M., AND HOPPE, H. 2006. Poisson Surface Reconstruction. In Symposium on Geometry Processing. 61-70.
  14. KOLLURI, R., SHEWCHUK, J., AND O'BRIEN, J. 2004. Spectral Surface Reconstruction from Noisy Point Clouds. In Symposium on Geometry Processing. 11-21.
  15. LINDSTROM, P. AND PASCUCCI, V. 2002. Terrain Simplification Simplified: A General Framework for View-Dependent Out-of-Core Visualization. IEEE TVCG 8, 3, 239-254.
  16. OHTAKE, Y., BELYAEV, A., ALEXA, M., TURK, G., AND SEIDEL, H. 2003. Multi-level Partition of Unity Implicits. In ACM Siggraph. 463-470.
  17. SAMOZINO, M., ALEXA, M., ALLIEZ, P., AND YVINEC, M. 2006. Reconstruction with Voronoi Centered Radial Basis Functions. In Symposium on Geometry Processing. 51-60.
  18. SCHALL, O., BELYAEV, A., AND SEIDEL, H.-P. 2005. Robust filtering of noisy scattered point data. In IEEE/Eurographics Symposium on Point-Based Graphics. 71-77.

Cited by

  1. High-Quality Depth Map Generation of Humans in Monocular Videos vol.20, pp.2, 2014, https://doi.org/10.15701/kcgs.2014.20.2.1
  2. High-Quality Depth Estimation Using an Exemplar 3D Model for Stereo Conversion vol.21, pp.7, 2015, https://doi.org/10.1109/TVCG.2015.2398440
  3. Stereoscopic image generation of background terrain scenes vol.22, pp.2-3, 2011, https://doi.org/10.1002/cav.415