Scale Consistent Image Completion

Holtzman-Gazit, Michal; Yavneh, Irad

doi:10.1007/11919476_65

Cited by 3 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This adds up to just a fraction more than cost of producing C(I n )-the usual completion of a single image. In particular, this implementation is far more efficient than that used in (Holtzman-Gazit & Yavneh, 2006), while yielding improved results.…”

Section: Computational Complexitymentioning

confidence: 99%

“…Our aim is to show how to improve the robustness of image completion procedures by incorporating them in a novel scale consistent framework. The basic ideas were introduced by the authors in (Holtzman-Gazit & Yavneh, 2006). However, the realization of these ideas suffered from several drawbacks, which are overcome in this paper as described in detail below.…”

Section: Introductionmentioning

confidence: 99%

“…Presently, the algorithm costs only a fraction more than the algorithm of Criminisi et al that it is based on, and yet its results are consistently and substantially better. Another drawback in (Holtzman-Gazit & Yavneh, 2006) is sensitivity to inadequate completions of the smoothest version of the image. This is overcome by the new algorithm introduced here, which promotes flow of information from fine to coarse scales.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Scale-Consistent Approach to Image Completion

Holtzman-Gazit

Yavneh

2008

Int J Mult Comp Eng

Self Cite

View full text Add to dashboard Cite

Most patch based algorithms for completing missing parts of images fill in the absent regions by copying patches from the known part of the image into the unknown part, somewhat like plastic surgery. The criterion for deciding which patch to copy is compatibility of the copied patch with the vicinity of the region being completed. In this paper we propose introducing a new dimension to this compatibility criterion, namely, scale. The patch is thus chosen by evaluating its consistency with respect to a hierarchy of smoothed (less detailed) versions of the image, as well as its surroundings in the current version. Applied recursively, this approach results in a multi-scale framework that is shown to yield a dramatic improvement in the robustness of patch based image completion.

show abstract

Section: Computational Complexitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation