Edge-preserving decompositions for multi-scale tone and detail manipulation

By Zeev Farbman, Raanan Fattal, Dani Lischinski, Richard Szeliski. ACM Transactions on Graphics, 2008

486 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6237447c36e60d69d19d92fde328071b73d10db7

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Guided Image Filtering (2010, methodology): “Though this filter is effective in many situations, it may have unwanted gradient reversal artifacts [15], [16], [8] near edges (discussed in Section 3.4).”
Classification-Driven Dynamic Image Enhancement (2017, methodology): “Examples of such enhancement methods include Gaussian smoothing, anisotropic diffusion, weighted least squares (WLS), and bilateral ﬁltering.”
Transfusive image manipulation (2012, background): “…as image colorization [Levin et al. 2004], edge-aware editing of tonal values [Lischinski et al. 2006], edge-aware multiscale image representation [Farbman et al. 2008], or interactions between distant pixels [An and Pellacini 2008] (see the surveys in e.g. [Li et al. 2008; Farbman et al. 2010]).”
Fast End-to-End Trainable Guided Filter (2018, methodology): “Method L0 Smoothing [7] Detail Manipulation [3] Style Transfer [11] Non-local Dehazing [4] Image Retouching [2] MSE PSNR SSIM MSE PSNR SSIM MSE PSNR SSIM MSE PSNR SSIM MSE PSNR SSIM DGFb 27 34.”
LIME: Low-Light Image Enhancement via Illumination Map Estimation (2017, background): “Since (I + ∑d∈{u,v} DT d Diag(w̃d)Dd) is a symmetric positive definite Laplacian matrix, there are many techniques available for solving it, for example, [28]–[32].”
Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images (2018, methodology): “The decomposition is performed by applying the weighted least squares (WLS) method [54] to each channel.”
Enhancing underwater images and videos by fusion (2012, result): “We demonstrate that the simple Laplacian pyramid yields effective results comparable with the recent edge preserving filters such as WLS [10].”
Color Balance and Fusion for Underwater Image Enhancement (2018, background): “A common solution to overcome this limitation is to employ multi-scale linear [57], [59] or non-linear filters [60], [61].”
Low-Light Image Enhancement With Semi-Decoupled Decomposition (2020, methodology): “(e) WLS [30] (λ = 1, α = 1.”
Pixel-level image fusion: A survey of the state of the art (2017, background): “…pyramid[4], wavelet [5, 11, 12], complex wavelet [13], curvelet[14, 15], contourlet [16–23], shear-let [24–26], edge-preserving decompositions[27– 29], anisotropic heat diﬀusion[30], log-Gabor transform[31], support value transform [32, 33], optimal scale transform [34, 35] coeﬃcient [4,…”
The Fast Bilateral Solver (2015, methodology): “Our pixel-space loss (Eq 1) resembles that of weighted least squares filtering [8, 9, 31], with one critical difference being our use of bilateral-space optimization which allows for efficient optimization even when using a large spatial support in the bilateral affinity, thereby improving the quali”
A fusion-based enhancing method for weakly illuminated images (2016, background): “WLS [40]) generate similar result while requiring a complex computation.”