UCSC Logo

UNIVERSITY OF CALIFORNIA
SANTA CRUZ
MDSP Logo

Nonlocal Image Editing

Hossein Talebi, Peyman Milanfar



 

Abstract:

In this work we introduce a new image editing tool, based on the spectrum of a global filter computed from image affinities. Recently, it has been shown that the global filter derived from a fully connected graph representing the image, can be approximated using the Nystrom extension [1]. This filter is computed by approximating the leading eigenvectors of the filter. These orthonormal eigenfunctions are highly expressive of the coarse and fine details in the underlying image, where each eigenvector can be interpreted as one scale of a data-dependent multiscale image decomposition. In this filtering scheme, each eigenvalue can boost or suppress the corresponding signal component in each scale. Our analysis shows that the mapping of the eigenvalues by an appropriate polynomial function endows the filter with a number of important capabilities, such as edge-aware sharpening, denoising, tone manipulation and abstraction, to name a few. Furthermore, the edits can be easily propagated across the image.

Manuscript:

H. Talebi and P. Milanfar, "Nonlocal Image Editing", IEEE Transactions on Image Processing, vol. 23, No. 10, pp. 4460-4473, October 2014. (PDF)


MATLAB Code:

This software is provided for non-commercial research purposes only. Use at your own risk. No warranty is implied by this distribution. Copyright © 2014 by University of California. (Download) (last update: September/20/2014)


Examples:

  1. Eigenvectors of the NLM kernel without its spatial term: Fig. 1, Deer, Bird, JFK
  2. Eigenvectors of the NLM kernel including its spatial term: Fig. 3, Deer, Bird, JFK
  3. Detail Manipulation: Fig. 7, Fig. 8, Fig. 9, Fig. 10, Leaf
  4. Globalizing Mask: Fig. 11
  5. Globalized Edit: Fig. 12, Fig. 13, Bridge, Rock
  6. Recoloring: Fig. 14, Fig. 15, Pills
  7. Colorization: Fig. 16, Chrysler Building, Bunny (failed case)
  8. Fake Depth of Field: Fig. 17, Cup
  9. Abstraction: Fig. 18, Tree, Island

 


References:

[1] H. Talebi, P. Milanfar, "Global Image Denoising", IEEE Transactions on Image Processing, vol. 23, No. 2, pp. 755-769, February 2014. (PDF)