Generation of Multi-view Images Using Depth Map Decomposition and Edge Smoothing

깊이맵의 정보 분해와 경계 평탄 필터링을 이용한 다시점 영상 생성 방법

  • Kim, Sung-Yeol (Department of Information and Communications, Gwangju Institute of Science and Technology(GIST)) ;
  • Lee, Sang-Beom (Department of Information and Communications, Gwangju Institute of Science and Technology(GIST)) ;
  • Kim, Yoo-Kyung (Department of Information and Communications, Gwangju Institute of Science and Technology(GIST)) ;
  • Ho, Yo-Sung (Department of Information and Communications, Gwangju Institute of Science and Technology(GIST))
  • 김성열 (광주과학기술원 정보통신공학과) ;
  • 이상범 (광주과학기술원 정보통신공학과) ;
  • 김유경 (광주과학기술원 정보통신공학과) ;
  • 호요성 (광주과학기술원 정보통신공학과)
  • Published : 2006.12.29

Abstract

In this paper, we propose a new scheme to generate multi-view images utilizing depth map decomposition and adaptive edge smoothing. After carrying out smooth filtering based on an adaptive window size to regions of edges in the depth map, we decompose the smoothed depth map into four types of images: regular mesh, object boundary, feature point, and number-of-layer images. Then, we generate 3-D scenes from the decomposed images using a 3-D mesh triangulation technique. Finally, we extract multi-view images from the reconstructed 3-D scenes by changing the position of a virtual camera in the 3-D space. Experimental results show that our scheme generates multi-view images successfully by minimizing a rubber-sheet problem using edge smoothing, and renders consecutive 3-D scenes in real time through information decomposition of depth maps. In addition, the proposed scheme can be used for 3-D applications that need the depth information, such as depth keying, since we can preserve the depth data unlike the previous unsymmetric filtering method.

본 논문은 깊이맵의 정보 분해(information decomposition)와 적응적 경계 평탄 필터링(adaptive edge smooth filtering)을 이용하여 다시점 영상을 생성하는 방법을 제안한다. 제안한 방법은 깊이맵의 경계 영역에 평탄 필터링을 수행한 후, 깊이맵을 네 가지 종류의 분해 영상, 즉, 규칙 메쉬 영상, 경계 영상, 특징점 영상, 계층의 수 영상으로 변환한다. 그런 다음, 네 가지의 분해 영상에 3차원 메쉬 표현법을 적용하여 3차원 장면을 생성하고, 3차원 공간에서 가상 카메라의 위치를 변경하여 생성한 3차원 장면으로부터 다시점 영상을 추출한다. 실험 결과는 제안한 방법이 rubber-sheet 문제를 최소화하여 다시점 영상을 성공적으로 생성할 수 있었고, 깊이맵의 정보 분해를 통해 실시간으로 3차원 장면을 렌더링할 수 있었음을 보여준다. 또한, 제안한 방법은 기존의 방법과 달리 깊이맵 정보를 보존하기 때문에, 깊이 키잉(depth keying)과 같이 깊이 정보를 이용하는 3차원 응용에 활용할 수 있다.

Keywords

References

  1. C. Fehn, E. La Barre, and S. Pastoor, 'Interactive 3-D TV concepts and key technologies,' Proceedings of the IEEE, vol. 94, no. 3, pp. 524-538, 2006 https://doi.org/10.1109/JPROC.2006.870688
  2. A. Ignatenko and A. Konushin, 'A framework for depth imagebased modeling and rendering,' Proc. Graphicon, pp. 169-172, 2003
  3. C. Zitnick and T. Kanade, 'A cooperative algorithm for stereo matching and occlusion detection,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 7, pp. 675-684, 2000 https://doi.org/10.1109/34.865184
  4. S.M. Kim, J. Cha, J. Ryu, and K.H. Lee, 'Depth video enhancement of haptic interaction using a smooth surface reconstruction,' IEICE Trans. on Information and System, vol. E89-D, pp. 37-44, 2006 https://doi.org/10.1093/ietisy/e89-d.1.37
  5. J. Shade, S. Gotler, and R. Szeliski, 'Layered depth images,' SIGGRAPH, pp. 291-298, 1998
  6. S. Grewatsch and E. Muller, 'Fast mesh-based coding of depth map sequences for efficient 3D video reproduction using OpenGL,' Proc. of International Conference on Visualization, Imaging and Image Processing, 2005
  7. B. Chai, S. Sethuraman, H. Sawhey, and P. Hatract, 'Depth map compression for real-time view-based rendering,' Pattern Recognition Letters, vol. 25, pp. 755-766, 2004 https://doi.org/10.1016/j.patrec.2004.01.002
  8. W.R. Mark, L. McMillan, and G. Bishop, 'Post-rendering 3D warping,' Proc. of Symposium on Interactive 3D Graphics, pp. 7-16, 1997
  9. L. Zhang and W. J. Tam, 'Stereoscopic image generation based on depth images for 3D TV,' IEEE Trans. on Broadcasting, vol. 51, pp. 191-199, 2005 https://doi.org/10.1109/TBC.2005.846190
  10. R. Gvili, A. Kaplan, E. Ofek, and G. Yahav, 'Depth keying,' SPIE Electronic Imaging, vol. 5006, pp. 564-574, 2003
  11. 이상범, '깊이맵의 전처리를 통한 다시점 영상 생성 방법,' 광주과학기 술원 석사논문, 2006
  12. C. Zitnick, S. Kang, M. Uyttendaele, S. Winder, and R. Szeliski, 'High-quality video view interpolation using a layered representation,' SIGGRAPH, pp. 600-608, 2004
  13. P. Toft, 'Radon transform: theory and implementation,' Ph.D. Thesis, Informatics and Mathematical Modelling, Technical University of Denmark, 1996
  14. J.T. Tou and R.C. Gonzalez, Pattern recognition principles, Addison-Wesley Publishing Company, 1974