New edge-directed interpolation

By Xin Li, Michael T. Orchard. 2001

2,285 citations recorded by the source corpus.

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, methodology): “The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.”
Enhanced Deep Residual Networks for Single Image Super-Resolution (2017, methodology): “To solve the super-resolution problem, early approaches use interpolation techniques based on sampling theory [1, 15, 34].”
Super resolution using edge prior and single image detail synthesis (2010, background): “, [1, 14, 4, 27]) have their foundations in sampling theory and try to interpolate the HR image from the LR input.”
Color filter array demosaicking: new method and performance measures (2003, methodology): “We demonstrate in this section the efficacy of our proposed method by comparing it with six existing demo-saicking methods—bilinear interpolation, Freeman’s method [3], Hamilton’s method [7], Kimmel’s method [13], Li’s method [14], and Gunturk’s method [15].”
Nonlocal Image Restoration With Bilateral Variance Estimation: A Low-Rank Approach (2013, methodology): “Next, we compare SAIST-based image interpolation and three other leading methods (bicubic, NEDI [45] and SAI [50]) for regularly-decimated samples.”
Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization (2010, methodology): “As a classic method, the autoregressive (AR) modeling has been successfully used in image compression [33] and interpolation [34],”
Anchored Neighborhood Regression for Fast Example-Based Super-Resolution (2013, methodology): “Super-resolution algorithms can be roughly subdivided into three subclasses: interpolation methods like Lanczos upsampling [5] and New Edge Directed Interpolation (NEDI) [10], multi-frame methods [6, 7, 11] which make use of the presence of aliasing in multiple frames of the same scene to produce on”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, methodology): “Prior to the deep-learning era, numerous SR algorithms have been proposed based on the sampling theory [53,51], edge-guided interpolation [4,64,120], natural image priors [56,109], patch-exemplars [14,32] and sparse representations [113,112].”
Digital inpainting based on the Mumford–Shah–Euler image model (2002, neutral): “As scattered as the applications are, the methods for the inpainting related problems have also been very diversified, including the nonlinear filtering method, the Bayesian method, wavelets and spectral method, and the learning-and-growing method (especially for textures) (see, for example, recent ”
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss (2018, methodology): “One classic SR method is the interpolation-based approach, such as cubicbased [16], edge-directed [1, 26] and wavelet-based [36] methods.”
Single image super-resolution using Gaussian process regression (2011, methodology): “NEDI stands for new edge-directed interpolation [13].”
Linear demosaicing inspired by the human visual system (2005, neutral): “We also thank Antonio Torralba and Jean-Marc Vesin for fruitful discussions.”
SRFeat: Single Image Super-Resolution with Feature Discrimination (2018, methodology): “To overcome this limitation, and to enhance edges, edge preserving interpolation [18, 19] and edge prior-based approaches [20–22] were proposed.”
An edge-guided image interpolation algorithm via directional filtering and data fusion (2006, methodology): “algorithm achieves the highest PSNR results on all test images, except for image Lena, for which it has a slightly lower PSNR than the method in [9].”
A chronology of interpolation: from ancient astronomy to modern signal and image processing (2002, background): “…where the potential advantages of adaptive interpolation approaches have been demonstrated are image resolution enhancement or zooming [205], [336]–[342], spatial and temporal coding or compression of images and image sequences [343], [344], texture mapping [250], and volume rendering [345].”
Directionlets: anisotropic multidirectional representation with separable filtering (2006, methodology): “Some other methods involve directionally adaptive processing in order to preserve edges in images [32]–[35], whereas the methods proposed in [36], [37] impose”
Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis (2012, methodology): “We consider the second case in this paper, and the super-resolution problem can be viewed as an image interpolation problem [12, 29, 15, 21].”
Image hallucination with primal sketch priors (2003, methodology): “Edge-based interpolation methods [2, 15] have also been proposed.”