Fast median and bilateral filtering

By Ben Weiss. ACM Transactions on Graphics, 2006

416 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ba791fc6f34fed7a2cf8b7f174a19ee87fb05012

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Image smoothing via L0 gradient minimization (2011, methodology): “Edge-preserving smoothing can be achieved by local filtering, including bilateral filtering [Tomasi and Manduchi 1998], its accelerated versions [Paris and Durand 2006; Weiss 2006; Chen et al. 2007] and relatives [Choudhury and Tumblin 2003; Fattal 2009; Baek and Jacobs 2010; Kass and Solomon 2010].”
Real-time O(1) bilateral filtering (2009, neutral): “Several efficient numerical schemes [9, 17, 18, 19, 20] enable it to be computed at”
Visual Tracking via Locality Sensitive Histograms (2013, methodology): “They are computed at each pixel location, and have been proved to be very useful for many tasks like the bilateral filtering [25, 16], median filtering [25, 12] and tracking [15, 1].”
Edge-preserving decompositions for multi-scale tone and detail manipulation (2008, background): “Although a naı̈ve implementation of the filter is costly, several fast approximations have been proposed [Durand and Dorsey 2002; Paris and Durand 2006; Weiss 2006; Chen et al. 2007].”
Real-time edge-aware image processing with the bilateral grid (2007, background): “However, recent work has demonstrated acceleration and obtained good performance on CPUs, on the order of one second per megapixel [Durand and Dorsey 2002; Pham and van Vliet 2005; Paris and Durand 2006; Weiss 2006].”
Rolling Guidance Filter (2014, methodology): “Since acceleration of edge-aware filtering was well studied, many tools are available [8,19,28,22,33,32,2,1,11,12,13].”
Coherent line drawing (2007, methodology): “Since our ETF construction filter is essentially a modified bilateral filter, it may be possible to employ existing acceleration schemes [Durand and Dorsey 2002; Weiss 2006].”
Border detection in dermoscopy images using statistical region merging (2008, methodology): “This can be further reduced by using faster algorithms for median filtering (22) and morphological dilation (23).”
A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach (2006, methodology): “For these cases, one should prefer per-channel filtering and since the kernel is small, the iterated-box method (Weiss 2006) seems an appropriate choice.”
Median Filtering in Constant Time (2007, methodology): “Since Weiss’ Pixfoliate software is only available on the PowerPC architecture, comparison was only carried out on this platform.”
Guided Image Filtering (2010, methodology): “Under this viewpoint, both [34] and [18] sample the signal along the range domain but do not reconstruct it.”
Fast Image Processing with Fully-Convolutional Networks (2017, background): “The bilateral filter in particular has benefitted from long-term investment in its acceleration [21, 72, 15, 59, 2, 1, 29, 8].”
Joint bilateral upsampling (2007, methodology): “Durand and Dorsey [2002] applied the bilateral ﬁl-ter to HDR tone mapping and also described a fast approximation, which was recently improved upon [Paris and Durand 2006; Weiss 2006].”
Constant time O(1) bilateral filtering (2008, methodology): “Timing was conducted on a PowerMac G5 1.6 GHz for Weiss’s method, and on a P4 3.2 GHz for the others.”