Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement

By Jian Sun, Zongben Xu, Harry Shum. IEEE Transactions on Image Processing, 2011

328 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/16758855b5a89cf7ffa391aa64caa42532a48246

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

SRFeat: Single Image Super-Resolution with Feature Discrimination (2018, methodology): “To overcome this limitation, and to enhance edges, edge preserving interpolation [3, 29] and edge prior-based approaches [4, 8, 43] were proposed.”
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.”
Balanced Two-Stage Residual Networks for Image Super-Resolution (2017, methodology): “Image statistics based methods utilize the statistical edge information to reconstruct HR images, for example, in [6, 32].”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “Human Subject Studies We use the Berkeley segmentation dataset [32] to carry out the experiments as the images are diverse and widely used for SR evaluation [7, 10, 12].”
Super-resolution: a comprehensive survey (2014, methodology): “These algorithms [138,202,279,286,287,362,368,394,407, 431,445,500,520,546] similar to their peer multiple imagebased SR algorithms try to address the aliasing artifacts that”
Structure-Preserving Super Resolution With Gradient Guidance (2020, background): “[39] propose a gradient profile prior to represent image gradients and a gradient field transformation to enhance sharpness of super-resolved images.”
TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution (2024, background): “Early works often employ interpolation [17] or various image priors [18], [19], [20] to constrain the infinite solution space.”
No-Reference Image Sharpness Assessment in Autoregressive Parameter Space (2015, background): “valuable applications in image processing, such as automatic contrast enhancement [9], [10], super-resolution [11] and”
Single image super-resolution from transformed self-exemplars (2015, methodology): “Instead of learning in the 2D patch domain , some methods learn how 1D edge profiles transform across resolutions [30] [11].”