Advanced Search

Fast and Robust Pyramid-based Image Processing

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Frédo Durand Paris, Sylvain en_US Hasinoff, Samuel W. en_US Kautz, Jan en_US Aubry, Mathieu Durand, Frédo
dc.contributor.other Computer Graphics en 2011-11-15T16:30:09Z 2011-11-15T16:30:09Z 2011-11-15
dc.description.abstract Multi-scale manipulations are central to image editing but they are also prone to halos. Achieving artifact-free results requires sophisticated edgeaware 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 that yields speed-ups on the order of 50x. 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. en_US
dc.format.extent 11 p. en_US
dc.relation.ispartofseries MIT-CSAIL-TR-2011-049
dc.subject Computational photography, photoediting, image processing, Laplacian pyramid, bilateral filter, photographic style transfer en_US
dc.title Fast and Robust Pyramid-based Image Processing en_US
dc.language.rfc3066 en-US
dspace.orderedauthors Aubry, Mathieu; Paris, Sylvain; Hasinoff, Samuel W.; Kautz, Jan; Durand, Frédo

Files in this item

Name Size Format Description
MIT-CSAIL-TR-2011 ... 23.12Mb PDF

This item appears in the following Collection(s)

Show simple item record