Structure-Texture Image Decomposition—Modeling, Algorithms, and Parameter Selection

By Jean-François Aujol, Guy Gilboa, Tony F. Chan, Stanley J. Osher. International Journal of Computer Vision, 2006

702 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/27beafdc3153a4bf41332849a5911b8f830d5b8f

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

Fast Global Minimization of the Active Contour/Snake Model (2007, methodology): “Proof of Proposition 2 The proof is the same as the one proposed in [21, 41].”
A Duality Based Approach for Realtime TV-L1 Optical Flow (2007, methodology): “The following derivation is based on [4], but adapted to the stereo/optical flow setting.”
Nonlocal Operators with Applications to Image Processing (2008, methodology): “To solve (4.3) we generalize the algorithm of [3].”
Intrinsic Decompositions for Image Editing (2017, unknown): “This separates the high frequency textural elements from lower frequency structures [AGCO06].”
An introduction to Total Variation for Image Analysis (2009, background): “2 Total variation with L(1) data fidelity term Similar to the (ROF ) model, the TV − L1 model [61, 25, 12] is defined as the variational problem min u { ∫”
Optical flow modeling and computation: A survey (2015, methodology): “Another successful optimization method based on alternate minimization of simple sub-problems has been proposed by [8] and used for optical ﬂow in [285].”
Stereoscopic Scene Flow Computation for 3D Motion Understanding (2011, background): “Alternative invariant features can be derived from a structure-texture image decomposition as introduced in Aujol et al. (2006).”
Fast Image Processing with Fully-Convolutional Networks (2017, background): “Other work has examined the acceleration of variational methods [6, 62, 13, 17], gradient-domain techniques [46], convolutions with large spatial support [23], and local Laplacian filters [5].”
Signal Recovery by Proximal Forward-Backward Splitting (2005, background): “The variational formulations proposed in [5, 6, 7, 71, 72] to achieve this decomposition based on a noisy observation z ∈ H of the signal of interest are of the general form (4.10) minimize where ψ and φ are in Γ 0 ( H ) and ρ ∈ ]0 , + ∞ [.”
An Improved Algorithm for TV-L 1 Optical Flow (2009, methodology): “The following derivation is based on [4], but adapted to the stereo/optical flow setting.”