Fast Local Laplacian Filters: Theory and Applications

Mathieu Aubry, Sylvain Paris, Samuel W. Hasinoff, Jan Kautz, Frédo Durand

Photo is broken


Multi-scale manipulations are central to image editing but they are also prone to halos. Achieving artifact-free results requires sophisticated edge- aware techniques and careful parameter tuning. These shortcomings were recently addressed by the local Laplacian filters, which can achieve a broad range of effects using standard Laplacian pyramids. However, these filters are slow to evaluate and their relationship to other approaches is unclear. In this paper, we show that they are closely related to anisotropic diffusion and to bilateral filtering. Our study also leads to a variant of the bilateral filter that produces cleaner edges while retaining its speed. Building upon this result, we describe an acceleration scheme for local Laplacian filters on gray-scale images that yields speed-ups on the order of 50×. Finally, we demonstrate how to use local Laplacian filters to alter the distribution of gradients in an image. We illustrate this property with a robust algorithm for photographic style transfer.


You can download the matlab code for Local Laplacian Filters and style transfer here (4.1 MB)


You can download our SIGGRAPH 2014 in PPTX (23MB) or PDF (4MB, without the animations).

Supplementary material

You can see more results and comparisons here


Article thumbnail

Fast Local Laplacian Filters: Theory and Applications

M. Aubry, S. Paris, S. Hasinoff, J. Kautz and F. Durand

ACM Transactions on Graphics, 2014 (to appear)

Download pdf | bibtex | View project web page on local laplacian filters

Copyright Notice

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright.