This documentation is for version 1.0 of Inpaint.
Inpaint (a.k.a. content-aware fill) the areas indicated by the Mask input using patch-based inpainting.
Be aware that this filter may produce different results on each frame of a video, even if there is little change in the video content. To inpaint areas with lots of details, it may be better to inpaint on a single frame and paste the inpainted area on other frames (if a transform is also required to match the other frames, it may be computed by tracking).
A tutorial on using this filter can be found at http://blog.patdavid.net/2014/02/getting-around-in-gimp-gmic-inpainting.html
The algorithm is described in the two following publications:
“A Smarter Examplar-based Inpainting Algorithm using Local and Global Heuristics for more Geometric Coherence.” (M. Daisy, P. Buyssens, D. Tschumperlé, O. Lezoray). IEEE International Conference on Image Processing (ICIP‘14), Paris/France, Oct. 2014
“A Fast Spatial Patch Blending Algorithm for Artefact Reduction in Pattern-based Image Inpainting.” (M. Daisy, D. Tschumperlé, O. Lezoray). SIGGRAPH Asia 2013 Technical Briefs, Hong-Kong, November 2013.
Uses the ‘inpaint’ plugin from the CImg library.
CImg is a free, open-source library distributed under the CeCILL-C (close to the GNU LGPL) or CeCILL (compatible with the GNU GPL) licenses. It can be used in commercial applications (see http://cimg.eu). The ‘inpaint’ CImg plugin is distributed under the CeCILL (compatible with the GNU GPL) license.
|Parameter / script name||Type||Default||Function|
|Patch Size /
|Lookup Size /
|Lookup Factor /
|Blend Size /
|Blend Threshold /
|Blend Decay /
|Blend Scales /
|Allow Outer Blending /
||Boolean||Off||Divide the image by the alpha channel before processing, and re-multiply it afterwards. Use if the input images are premultiplied.|
|Invert Mask /
||Boolean||Off||When checked, the effect is fully applied where the mask is 0.|
||Double||1||Mix factor between the original and the transformed image.|