An Efficient Walkthrough from Two Images using Spidery Mesh Interface and View Morphing

Spidery 매쉬 인터페이스와 뷰 모핑을 이용한 두 이미지로부터의 효율적인 3차원 애니메이션

  • Cho, Hang-Shin (Electronics and Telecommunications Research Institute) ;
  • Kim, Chang-Hun (Electronics and Telecommunications Research Institute)
  • Published : 2001.04.01

Abstract

This paper proposes an efficient walktlu-ough animation from two images of the same scene. To make animation easily and fast, Tour Into the Picture(TIP) enables walkthrough animation from single image but lacks the reality of its foreground object when the viewpoint moves from side to side, and view morphing uses only 2D transition between two images but restricts its camera path on the line between two views. By combining advantages of these two image-based techniques, this paper suggests a new virtual navigation technique which enable natural scene transformation when the viewpoint changes in the side-to-side direction as well as in the depth direction. In our method, view morphing is employed only in foreground objects , and background scene which is perceived carelessly is mapped into cube-like 3D model as in TIP, so as to save laborious 3D reconstruction costs and improve visual realism simultaneously. To do this, we newly define a camera transformation between two images from the relationship of the spidery mesh transformation and its corresponding 3D view change. The result animation shows that our method creates a realistic 3D virtual navigation using a simple interface.

본 논문은 동일 장면을 나타내는 한 쌍의 이미지를 이용한 효율적인 3차원 애니메이션 기법을 제안한다. 간단하고 빠른 애니메이션을 위해 그림 속으로의 영향은 한 장의 이미지에서 시점의 깊이 이동을 가능하게 하지만 전경물체의 표현이 시점의 좌우 변환의 사실감을 고려하지 않으며, 뷰모핑은 두 장의 이미지 사이의 2차원 변환만을 이용하지만 시점의 이동이 두 카메라의 중심을 잇는 선상으로 제한된다는 단점이 있다. 본 논문은 두 기법의 단점을 서로 보완하여 시점의 깊이 이동뿐 아니라 좌우이동에서도 자연스러운 영상을 생성하는 새로운 애니메이션 기법을 제안한다. 본 논문에서는 배경 장면을 spidery 매쉬로부터 복원된 간단한 직육면체에 매핑하고, 관찰자가 주의 깊게 인식하고 전경물체에 대해서는 두 입력 이미지의 투영중심을 잇는 직선상에 평행한 시점의 이동에만 제한적으로 뷰모핑을 적용하여 장면전체의 이미지 픽셀들에 대한 3차원 정보의 복원 비용을 줄이면서도 시점이동의 사실감을 높인다. 두 전경물체 사이의 선형보간 파라미터는 두 spidery 메쉬 간의 차이와 이에 대응하는 배경모델에서의 3차원시점 변환과의 관계로부터 결정된다. 실험을 통해 제안방법이 간단한 인터페이스만으로도 사실감을 유지하는 자유로운 3차원 시점이동 애니메이션을 생성함을 보인다.

Keywords

References

  1. Ken-ichi Anjyo and Youichi Horry, Theory and Practice of 'Tour Into the Picture'. SIGGRAPH '98 Course Notes Lecture 8, ACM SIGGRAPH, 1998
  2. Thaddeus Beier and Shawn Neely, Feature-based Image metamorphosis, Proceedings of SIGGRAPH '92, pages 35-42, 1992 https://doi.org/10.1145/133994.134003
  3. Shenchang Eric Chen and Lance Williams, View interpolation for image synthesis, Proceedings of SIGGRAPH '93, pages 279-288, New York, 1993 https://doi.org/10.1145/166117.166153
  4. Shenchang Eric Chen, QuickTime VR- An Image-Based Approach to Virtual Environment Navigation, Proceedings of SIGGRAPH '95, pages 29-38, 1995 https://doi.org/10.1145/218380.218395
  5. Paul E. Debevec, Camillo J. Taylor, and Jitendra Malik, Modeling and rendering architecture from photographs:A hybrid geometry- and image-based approach, Proceedings of SIGGRAPH '96, pages 11-20, Addison-Wesley, 1996 https://doi.org/10.1145/237170.237191
  6. Paul E. Debevec, Modeling and rendering architecture from photographs, Ph.D Thesis at the University of California, Berkeley, Fall 1996
  7. Oliver Faugeras, Three-Dimensional Computer Vision- A Geometric Viewpoint, Massachusetts Institute of Technology,1993
  8. James J,Gibson, The Perception of Visual World. Houghton Mifflin, Boston 1950
  9. James. J,Gibson, The Ecological approach to Visual Perception. Lawrence Erlbaum Associates, Publishes, 1979
  10. Steven J. Gortler,Radek Grzeszczuk, Richard Szeliski, and Michael F. Cohen, The Lumigraph, Proceedings of SIGGRAPH '96, pages 43-54, 1996 https://doi.org/10.1145/237170.237200
  11. Youichi Horry, Keri-ichi Anjyo, and Kiyoshi Arai, Tour Into the Picture: Using a Spidery Mesh Interface to Make Animation from a Single Image, Proceedings of SIGGRAPH '97, pages 225-232, New York, 1997 https://doi.org/10.1145/258734.258854
  12. Mark Levoy and Pat Hanrahan, Light Field Rendering, Proceedings of SIGGRAPH '96, pages 31-42, 1996 https://doi.org/10.1145/237170.237199
  13. Seungyong Lee, George Wolberg, Kyung-Yong Chwa, and Sung Yang Shin, Image metamorphosis with Scattered Feature Constraints, In IEEE Transactions on visualization and Computer Graphics, vol. 2, no. 4., pages 337-354, December 1996 https://doi.org/10.1109/2945.556502
  14. Leonard McMillan and Gary Bishop, Plenoptic Modeling : An Image-Based Rendering System, Proceedings of SIGGRAPH '95, pages 39-46, 1995 https://doi.org/10.1145/218380.218398
  15. Daniel Scharstein, View Synthesis using Stereo Vision, Ph.D Thesis of Cornell University, 1997
  16. Steven M. Seitz, Image-based Transformation of viewpoint and scene appearance, Ph.D Thesis at the University of Wisconsin-Madison, 1997
  17. Steven M. Seitz and Charles R. Dyer, Complete Scene Structure from Four Point Correspondences, Proceedings of Fifth Intl. Conf. On Computer Vision, Cambridge MA, pages 330-337,1995
  18. Steven M. Seitz and Charles R. Dyer, Physically-Valid View Synthesis by Image Interpolation, Proceedings of Workshop on Representations of Visual Scenes, Cambridge MA, 1995 https://doi.org/10.1109/WVRS.1995.476848
  19. Steven M. Seitz and Charles R. Dyer, View Morphing, Proceedings of SIGGRAPH '96, pages 21-30, 1996 https://doi.org/10.1145/237170.237196
  20. Jonathan W. Shade, Steven J. Gortler, Li-wei He, and Richard Szeliski, Layered Depth Images, Proceedings of SIGGRAPH '98, pages 231-242, 1998 https://doi.org/10.1145/280814.280882
  21. Richard Szeliski, Video Mosaics for Virtual Environments, IEEE Computer Graphics & Applications, 16(2):22-30, March 1996 https://doi.org/10.1109/38.486677
  22. Richard Szeliski and Heung-Yeung shum, Creating Full View Panoramic Image Mosaics and Environment Maps, Proceedings of SIGGRAPH '97, pages 251-258, 1995 https://doi.org/10.1145/258734.258861
  23. Wolberg,G. Digital Image Warping. IEEE computer Society Press, Los Alamitos, CA. 1990
  24. Daniel N. Wood, Adam Finkelstein, John F. Hughes, and David H, Salesin. Multiperspective Panoramas for Cel Animation, Proceedings of SIGGRAPH '97, pages 243-250, 1997 https://doi.org/10.1145/258734.258859