Fragment-based image completion
- 1 July 2003
- proceedings article
- Published by Association for Computing Machinery (ACM)
- Vol. 22 (3) , 303-312
- https://doi.org/10.1145/1201775.882267
Abstract
We present a new method for completing missing parts caused by the removal of foreground or background elements from an image. Our goal is to synthesize a complete, visually plausible and coherent image. The visible parts of the image serve as a training set to infer the unknown parts. Our method iteratively approximates the unknown regions and composites adaptive image fragments into the image. Values of an inverse matte are used to compute a confidence map and a level set that direct an incremental traversal within the unknown area from high to low confidence. In each step, guided by a fast smooth approximation, an image fragment is selected from the most similar and frequent examples. As the selected fragments are composited, their likelihood increases along with the mean confidence of the image, until reaching a complete image. We demonstrate our method by completion of photographs and paintings.Keywords
This publication has 21 references indexed in Scilit:
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002
- Transferring color to greyscale imagesACM Transactions on Graphics, 2002
- Hierarchical pattern mappingACM Transactions on Graphics, 2002
- Self-similarity based texture editingACM Transactions on Graphics, 2002
- Synthesizing natural texturesPublished by Association for Computing Machinery (ACM) ,2001
- Image inpaintingPublished by Association for Computing Machinery (ACM) ,2000
- Completion energies and scalePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and SalienceNeural Computation, 1997
- Inferring global pereeptual contours from local featuresInternational Journal of Computer Vision, 1996
- Paint by numbers: abstract image representationsPublished by Association for Computing Machinery (ACM) ,1990