A New Image Completion Method Using Hierarchical Priority Belief Propagation Algorithm

계층적 우선순위 BP 알고리즘을 이용한 새로운 영상 완성 기법

  • Kim, Moo-Sung (Department of Computer Science, Catholic University of Korea) ;
  • Kang, Hang-Bong (Department of Computer Science, Catholic University of Korea)
  • 김무성 (가톨릭대학교 컴퓨터공학과) ;
  • 강행봉 (가톨릭대학교 컴퓨터공학과)
  • Published : 2007.09.25

Abstract

The purpose of this study is to present a new energy minimization method for image completion with hierarchical approach. The goal of image completion is to fill in missing part in a possibly large region of an image so that a visually plausible outcome is obtained. An exemplar-based Markov Random Field Modeling(MRF) is proposed in this paper. This model can deal with following problems; detection of global features, flexibility on environmental changes, reduction of computational cost, and generic extension to other related domains such as image inpainting. We use the Priority Belief Propagation(Priority-BP) which is a kind of Belief propagation(BP) algorithms for the optimization of MRF. We propose the hierarchical Priority-BP that reduces the number of nodes in MRF and to apply hierarchical propagation of messages for image completion. We show that our approach which uses hierarchical Priority-BP algorithm in image completion works well on a number of examples.

본 논문은 영상 완성(image completion)을 위해 계층적으로 적용되는 새로운 에너지 최적화 방식을 제안한다. 영상 완성의 목적은 영상의 특정 영역이 지워진 상태에서, 그 지워진 부분을 나머지 부분과 시각적으로 어울리도록 완성시키는 기법을 말한다. 본 논문에서는 전역적 특징의 탐지, 주변 환경 변화에 대한 유연성, 계산비용의 감소, 영상 인페인팅과 같은 관련기법들로의 확장성 문제들을 다룰 수 있도록 마르코프 랜덤 필드(Markov Random Field)로 모델링 된 예제 기반 방식(exampler-based mehtod) 접근법을 택한다. 그리고 MRF에서의 에너지 최적화를 위해 BP 알고리즘(Belief Propagation Algorithm)의 변형인 우선순위 BP 알고리즘(Priority-Belief Propagation Algorithm)을 적용하였다. 본 논문에서 제안한 계층적 우선순위 BP 알고리즘(Hierarchical Priority-Belief Propagation Algorithm)은 MRF의 정점의 수를 줄이고 메시지를 계층적으로 전파한다. 이렇게 계층적 우선순위 BP 알고리즘을 영상 완성에 적용하여 여러 영상들에서 바람직한 결과를 얻었다.

Keywords

References

  1. N. Komodakis and G. Tziritas, 'Image Completion Using Global Optimization,' in CVPR, 2006
  2. A. A. Efros and T. K. Leung, 'Texture synthesis by non-parametric sampling,' in ICCV, 1999
  3. D. J. Heeger, and J. R. Bergen, 'Pyramid-based texture analysis synthesis,' in Proceedings of SIGGRAPH, 1995
  4. V. Kwatra, I. Essa, A. Bobic, and N. Kwatra, 'Texture optimization for example-based synthesis,' in SIGGRAPH, 2005
  5. Y. Wexler, E. Shechtman, and M. Irani, 'Space-time video completion,' in CVPR, pages 120-127, 2004
  6. J. Sun, L. Yuan, J. Jia, and H.-Y. Shum, 'Image completion with structure propagation,' in SIGGRAPH, 2005
  7. V. Kwatra and et al. 'Graphcut textures: Image and video synthesis using graph cuts,' in SIGGRAPH, 2003
  8. I. Drori, D. Cohen-Or, and H. Yeshurn, 'Fragment-based image completion,' in SIGGRAPH, 2003
  9. A, Criminisi, P. Perez, and K. Toyam,. 'Object removal by exemplar-based inpainting,' in SIGGRAPH, 2000
  10. P. F. Felzenszwalb and D. P. Huttenlocher, 'Efficient belief propagation for early vision,' in CVPR, 2004
  11. Chris Bishop. 'Pattern Recognition and Machine Learning,' Springer. 359-422, 2006
  12. J. Yedida, W. T. Freeman, and Y. Weiss, 'Understanding belief propagation and its generalizations,' International Joint Conference on Artificial Intelligence (IJCAI), 2001
  13. J. Pearl, 'Probabilistic Reasoning in Intelligent Systems : Networks of Plausible inference,' Morgan Kaufmann Publishers Inc., 1988