Structure extraction from texture via relative total variation

By Li Xu, Qiong Yan, Yang Xia, Jiaya Jia. ACM Transactions on Graphics, 2012

941 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/bb2f018cb48c3d5b78fe0c264e285107fd979f6c

How researchers see this paper

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

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

StructureFlow: Image Inpainting via Structure-Aware Appearance Flow (2019, methodology): “We use σ in RTV [31] smooth method to control the maximum size of texture elements in Sgt. Smoother results are obtained with larger σ value.”
Rolling Guidance Filter (2014, methodology): “Xu et al. [30] optimized a global function with relative total variation (RTV) regularization.”
Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement (2020, background): “Here the first term is the fidelity and RTV(·) denotes the relative total variation term [38] (with a parameter ηt > 0).”
Constant Time Weighted Median Filtering for Stereo Matching and Beyond (2013, methodology): “9 we show a comparison with a recent sophisticated method in [29].”
Low-Light Image Enhancement With Semi-Decoupled Decomposition (2020, methodology): “1, we compare our method with several state-of-the-art edge-preserving ﬁlters, such as TV [27], GF [28], BLF [29], WLS [30], RTV [31], ROG [32], muGIF [33], SDTS [34] and LVD [4].”
Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network (2016, methodology): “4(b) and (c)), which reflect the main structures of an image, determine whether the image regions should be smoothed or not in the propagation step [11].”
Fast End-to-End Trainable Guided Filter (2018, background): “For example, image processing techniques enable smooth an image while preserving the edges [39, 41, 43], enhance the details of an image [13, 36], transfer style from a reference image [3, 4],”
Exploring Principles-of-Art Features For Image Emotion Recognition (2014, background): “[40] and their combination to measure gradation for each pixel.”
Toward Fast, Flexible, and Robust Low-Light Image Enhancement (2022, positive): “Further, Guo et al. [8] adopted the relative total variation [28] as the constraint of the illumination.”
Fast Global Image Smoothing Based on Weighted Least Squares (2014, methodology): “In our method, the default parameters for the total number of iterations T is set to 3, unless specified otherwise.”
Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior (2016, neutral): “[31] proposed an effective method for extracting the structure from texture via relative total variation (RTV).”
Deep Joint Image Filtering (2016, result): “(a) Input (b) RGF [9] (c) L0 [34] (d) Xu [8] (e) Ours (f) Kopf [33]”
STAR: A Structure and Texture Aware Retinex Model (2019, methodology): “The other way is to extract structure from the estimated texture weights [42].”
Joint Bi-layer Optimization for Single-Image Rain Streak Removal (2017, methodology): “Regarding the rain streaks as a texture superimposed over the background image, we employ the window inherent variation metric [30], which Figure 6: Guidance image computed by using [30] (left) and a result produced by using Ψ(B) alone (right).”
Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations (2020, methodology): “ten as follows: L rst= kI ost I stk 1 L rte= kI ote I gtk 1 (1) 6 Liu et al. where I gtis the ground truth image and I stis the structure image of I gt. We use an edge-preserving smoothing method RTV [35] to generate I stfollowing [26]. The hole regions in F teand F stare lled via structure and text”
Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration (2015, background): “, image structure extraction [57], we will have to make efforts to define the ground truth.”
Unnatural L0 Sparse Representation for Natural Image Deblurring (2013, background): “Xu and Jia [25] proposed a texture-removal strategy, explained and extended in [28], to guide edge selection and detect large-scale structures.”