Bilateral filtering for gray and color images

By Carlo Tomasi, Roberto Manduchi. 1998

Subfields: Computer Vision and Pattern Recognition

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

Non-local Neural Networks (2017, background): “Euclidean distance as used in [4, 47] is also applicable, but dot product is more implementation-friendly in modern deep learning platforms.”
Conditional Random Fields as Recurrent Neural Networks (2015, background): “Unlike the standard convolutional layer in which filters are fixed after the training stage, this new layer involves an edge-preserving filter [29, 23] that depends on the original spatial and appearance information of the image.”
Feature Denoising for Improving Adversarial Robustness (2018, methodology): “Our ablation studies show that using mean filters, median filters, and bilateral filters [21] for feature denoising also improves adversarial robustness, suggesting that feature denoising is a good design principle.”
Learning Affinity via Spatial Propagation Networks (2017, methodology): “Numerous methods explicitly design affinity matrices for image filtering [29, 10], colorization [15], matting [16] and image segmentation [14] based on the characterstics of the problem.”
View generation with 3D warping using depth information for FTV (2009, methodology): “Considering that the low-pass filter cannot smoothen the desired edge areas perfectly, we adopted bilateral filtering [10] for this purpose, which is defined in Eq.”
Total variation models for variable lighting face recognition (2006, methodology): “To reduce halo artifacts, discontinuity preserving filtering can be used to estimate L, such as anisotropic diffusion [28], bilateral filtering [40], or mean shift filtering [11].”
Noise Estimation from a Single Image (2006, background): “Adaptive Bilateral Filtering Bilateral filtering [17] is a simple and popular algorithm for feature-preserving image smoothing.”
Adaptive Support-Weight Approach for Correspondence Search (2006, methodology): “Equation (6) used for support-weight computation is very similar to the functions used for computing adaptive weights in structurepreserving noise filters such as those in [24], [25.”
PCA-Based Edge-Preserving Features for Hyperspectral Image Classification (2017, background): “The bilateral filter [40] and anisotropic diffusion [41] are”
A Survey of Black-Box Adversarial Attacks on Computer Vision Models (2019, background): “2) Bilateral Filter [87]:It is similar to Equation[45] but differs from it in its neighborhood Ω(i), which is a local region (e.”
A Tutorial on Speckle Reduction in Synthetic Aperture Radar Images (2013, background): “Bilateral Filtering– The bilateral filter (BF), originally introduced in [105] for gray scale images, has been recently extended to despeckling in [106].”
Image denoising with nonlocal spectral graph wavelets (2010, methodology): “Finally, computing filter weights incorporating both domain and range similarity underlies the older bilateral filtering approach [27].”
Enhancing underwater images and videos by fusion (2012, background): “The bilateral filter [28] [23] is one of the common solutions being an non-iterative edge-preserving smoothing filter that has proven usefull for several problems such as tone mapping, mesh smoothing and dual photography enhancement .”
CycleISP: Real Image Restoration via Improved Data Synthesis (2020, methodology): “(2) Averaging neighborhood values: in all directions using Gaussian kernel, in all directions only if pixels have similar values [56, 58] and along contours [42, 51].”
Fast Global Image Smoothing Based on Weighted Least Squares (2014, background): “Recent intensive efforts have led to several efficient techniques [3]–[7] to accelerate the bilateral filter, and also quite a few fast filtering approaches based on different theories and computational models [8]–[12].”