Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis

By Shenlong Wang, Lei Zhang, Yan Liang, Quan Pan. 2012

574 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Representation & Self-Supervised Learning

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

In Media Technology

In Representation & Self-Supervised Learning

Citations in the corpus

Coupled Generative Adversarial Networks (2016, methodology): “The same limitation is also applied to dictionary learning-based approaches [2, 4].”
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016, neutral): “Recent popular SISR methods can be classified into edge-based [35], image statisticsbased [9, 18, 46, 12] and patch-based [2, 43, 52, 13, 54, 40, 5] methods.”
HOGgles: Visualizing Object Detection Features (2013, methodology): “To do this, we solve a paired dictionary learning problem, inspired by recent super resolution sparse coding work [23, 21]:”
Studying Very Low Resolution Recognition Using Deep Networks (2016, background): “As explored previously [30], the mappings between LR and HR spaces are complex, spatial-variant and nonlinear.”
Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification (2018, methodology): “Two dictionary learning methods: semi-coupled dictionary learning method (SCDL) (Wang et al. 2012) and re-coupled dictionary learning (rCDL) (Huang and Frank Wang 2013) are adopted.”
Domain adaptive sparse representation-based classification (2015, background): “The first part of the cost function C1 with the constraint that diag(B) = 0 essentially exploits the self-expressiveness property of the data in the sense that each data point can be efficiently reconstructed by a combination of other points in the database.”
Partial Multi-Modal Sparse Coding via Adaptive Similarity Structure Regularization (2016, methodology): “The problem of multi-modal sparse coding is to find succinct representation for multi-modal data using only a few coding coefficients, which has attracted considerable attention recently [10, 8, 16, 7, 4, 3, 2, 9, 12].”
Accurate Blur Models vs. Image Priors in Single Image Super-resolution (2013, background): “Developing sophisticated image priors has been the focus of much single image SR research in the past decade, with many significant successes [7, 20, 23, 8, 6, 9, 21, 27, 25, 5, 19, 22, 1, 8, 13].”
Generalized Domain-Adaptive Dictionaries (2013, background): “[24] proposed learning dictionary pairs for cross-modal synthesis.”
Fast Direct Super-Resolution by Simple Functions (2013, methodology): “(a) Wang [21] (b) Freedman [3] (c) Sun [16] (d) Proposed”
Single-Image Super-Resolution: A Benchmark (2014, methodology): “While domain-specific SISR algorithms focus on specific classes of images such as faces [35,42], scenes [33], and graphics artwork [18], generic SISR algorithms [10,38,8,3,27,30,11,46,9,34,32,12,5,39,44,43] are developed for all kinds of images where the priors are typically based on primitive image”