Image completion using structural priority belief propagation

ABSTRACT

A new image completion algorithm called Structural Priority Belief Propagation (SPBP) is presented to deal with LDV based image completion in this paper. LDV completion is a new form of image completion based on another large displacement view (LDV) of the same scene, no wonder, it has the potential of repairing large unknown region with salient structure information. In order to complete such unknown region, SPBP makes two important extensions over existing Priority-BP: dynamic weight of structural consistency and structural priority inheritance so as to propagate linear structure with correct priority, meanwhile it promotes texture propagation adhering to a global optimization scheme. Experimental results demonstrate that SPBP can obtain more satisfactory results than other LDV completion algorithms and it also performs well for traditional single image completion.

REFERENCES

• 1: Connelly Barnes, Eli Shechtman, Adam Finkelstein, Dan B Goldman. PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing. ACM Trans. Graph. 28(3), 2009.
• 2: M. Bertalmio, G. Sapiro, V. Caselles, C. Ballester: Image inpainting. In ACM SIGGRAPH, pp. 417--424, 2000.
• 3: A. Criminisi, P. Perez, K. Toyama. Region °ling and object removal by exemplar-based image inpainting. IEEE Trans.Image Processing, 13(9), 2004.
• 4: I. Drori,D. Cohen-or, H. Yeshurum: Fragment-based image completion. ACM Trans. Graph. 22(3):303--312, 2003.
• 5: P. Felzenszwalb and D. Huttenlocher. Efficient Belief Propagation for Early Vision. IJCV, 70(1):41--54, 2006.
• 6: James Hays, Alexei A. Efros. Scene completion using millions of photographs. ACM Trans. Graph. 26(3), 2007.
• 7: T. Huang, et al. Image Inpainting by Global Structure and Texture Propagation. In ACM Multimedia, pp. 517--520, 2007.
• 8: J.-Y. Jia, C.-K. Tang: Image repairing: Robust image synthesis by adaptive ND tensor voting. In CVPR pp. 643--650, 2003.
• 9: N. Komodakis, G. Tziritas. Image Completion Using Global Optimization. In CVPR, 2006.
• 10: C. Liu, Y. Guo, L. Pan, Q. Peng, F. Zhang : Image completion based on views of large displacement. The Visual Computer 23, 9--11: 833--841, 2007.
• 11: C. Liu, Y. Yang, Q. Peng, J. Wang, W. Chen. Distortion Optimization based Image Completion from a Large Displacement View. Computer Graphics Forum, 27(7):1755--1764, 2008.
• 12: C. Strecha, T.Tuytelaars, L. Van Gool. Dense matching of multiple wide--baseline views. In ICCV pp. 1194--1201, 2003.
• 13: J. Sun, L. Yuan, J. Jia, H. Shum. Image completion with structure propagation. In ACM SIGGRAPH, pp. 861--868, 2005.
• 14: Q. Wu, Y. Yu. Feature matching and deformation for texture synthesis. ACM Trans. Graph. 23(3):364--367, 2004.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.m Miscellaneous

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.m Miscellaneous

General Terms:
Algorithms, Experimentation

Keywords:
image completion, large displacement view (LDV), structural priority belief propagation (SPBP)