An Efficient and Scalable Image Filtering Framework Using VIPS Fusion

Zhang, Jun; Chen, Xiuhong; Zhao, Yan; Li, H.

An Efficient and Scalable Image Filtering Framework Using VIPS Fusion

Date

2013

Authors

Zhang, Jun
Chen, Xiuhong
Zhao, Yan
Li, H.

Publisher

The Eurographics Association and Blackwell Publishing Ltd.

Abstract

Edge-preserving image filtering is a valuable tool for a variety of applications in image processing and computer vision. Motivated by a new simple but effective local Laplacian filter, we propose a scalable and efficient image filtering framework to extend this edge-preserving image filter and construct an uniform implementation in O(N) time. The proposed framework is built upon a practical global-to-local strategy. The input image is first remapped globally by a series of tentative remapping functions to generate a virtual candidate image sequence (Virtual Image Pyramid Sequence, VIPS). This sequence is then recombined locally to a single output image by a flexible edge-aware pixel-level fusion rule. To avoid halo artifacts, both the output image and the virtual candidate image sequence are transformed into multi-resolution pyramid representations. Four examples, single image de-hazing, multi-exposure fusion, fast edge-preserving filtering and tone-mapping, are presented as the concrete applications of the proposed framework. Experiments on filtering effect and computational efficiency indicate that the proposed framework is able to build a wide range of fast image filtering that yields visually compelling results.

        @article{10.1111:cgf.12247
,
journal = {Computer Graphics Forum},
title = {{An Efficient and Scalable Image Filtering Framework Using VIPS Fusion
}},
author = {Zhang, Jun and 
Chen, Xiuhong and 
Zhao, Yan and 
Li, H.
},
year = {2013
},
publisher = {The Eurographics Association and Blackwell Publishing Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.12247
}
}

URI

https://doi.org/10.1111/cgf.12247

Collections

32-Issue 7

Full item page