Single-Image Super-Resolution: A Benchmark

@inproceedings{Yang2014SingleImageSA,
  title={Single-Image Super-Resolution: A Benchmark},
  author={Chih-Yuan Yang and Chao Ma and Ming-Hsuan Yang},
  booktitle={ECCV},
  year={2014}
}
Single-image super-resolution is of great importance for vision applications, and numerous algorithms have been proposed in recent years. [] Key Method In addition to quantitative evaluations based on conventional full-reference metrics, human subject studies are carried out to evaluate image quality based on visual perception. The benchmark evaluations demonstrate the performance and limitations of state-of-the-art algorithms which sheds light on future research in single-image super-resolution.
Learning a No-Reference Quality Metric for Single-Image Super-Resolution
Fast single image super-resolution based on sigmoid transformation
TLDR
This paper proposes a fast and simple single image super-resolution strategy utilizing patch-wise sigmoid transformation as an imposed sharpening regularization term in the reconstruction, which realizes amazing reconstruction performance.
Real-World Single Image Super-Resolution: A Brief Review
Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model
TLDR
This paper builds a real-world super-resolution (RealSR) dataset where paired LR-HR images on the same scene are captured by adjusting the focal length of a digital camera and presents a Laplacian pyramid based kernel prediction network (LP-KPN), which efficiently learns per-pixel kernels to recover the HR image.
Edge-Informed Single Image Super-Resolution
TLDR
It is shown that the method of decoupling structure and texture reconstruction improves the quality of the final reconstructed high-resolution image.
Return of reconstruction-based single image super-resolution: A simple and accurate approach
TLDR
Through the (fast) iterative shrinkage-thresholding algorithm, a general, simple, yet accurate SISR framework is proposed by embedding off-the-shelf image denoising algorithms into the reconstruction process rather than struggling to develop advanced image priors.
A Deep Learning Based No-Reference Image Quality Assessment Model for Single-Image Super-Resolution
TLDR
A deep learning based no-reference image quality assessment (NR-IQA) model for SISR achieved a performance leap than state-of-the-art methods and proved the generalizability and the effectiveness of the proposed model.
Blind Super-Resolution with Deep Convolutional Neural Networks
TLDR
This paper addresses blind SR using Convolutional Neural Networks and shows that such models can handle different level of blur without any a priori knowledge of the actual kernel used to produce LR images.
FRESH—FRI-Based Single-Image Super-Resolution Algorithm
TLDR
This paper models images and, more precisely, lines of images as piecewise smooth functions and proposes a resolution enhancement method for this type of functions and applies this method along vertical, horizontal, and diagonal directions in an image to obtain a single-image super-resolution algorithm.
A comprehensive review of deep learning-based single image super-resolution
TLDR
This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super- resolution.
...
...

References

SHOWING 1-10 OF 58 REFERENCES
Fast Direct Super-Resolution by Simple Functions
TLDR
This paper proposes to split the feature space into numerous subspaces and collect exemplars to learn priors for each subspace, thereby creating effective mapping functions and facilitating both feasibility of using simple functions for super-resolution, and efficiency of generating high-resolution results.
Single image super-resolution using Gaussian process regression
TLDR
This paper proposes a framework for both magnification and deblurring using only the original low-resolution image and its blurred version, and shows that when using a proper covariance function, the Gaussian process regression can perform soft clustering of pixels based on their local structures.
Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior
  • K. Kim, Younghee Kwon
  • Computer Science, Mathematics
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2010
TLDR
Compared with existing algorithms, KRR leads to a better generalization than simply storing the examples as has been done in existing example-based algorithms and results in much less noisy images.
Super-resolution from internet-scale scene matching
  • Libin Sun, James Hays
  • Computer Science
    2012 IEEE International Conference on Computational Photography (ICCP)
  • 2012
TLDR
A key observation is that, even with extremely low-res input images, one can use global scene descriptors and Internet-scale image databases to find similar scenes which provide ideal example textures to constrain the image upsampling problem.
Super resolution using edge prior and single image detail synthesis
TLDR
This paper proposes an approach to extend edge-directed super-resolution to include detail from an image/texture example provided by the user (e.g., from the Internet), and can achieve quality results at very large magnification, which is often problematic for both edge- directed and learning-based approaches.
Super-resolution from a single image
TLDR
This paper proposes a unified framework for combining the classical multi-image super-resolution and the example-based super- resolution, and shows how this combined approach can be applied to obtain super resolution from as little as a single image (with no database or prior examples).
Patch based blind image super resolution
  • Q. Wang, Xiaoou Tang, H. Shum
  • Computer Science, Engineering
    Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
  • 2005
TLDR
The proposed method provides an automatic and stable way to compute super-resolution and the achieved result is encouraging for both synthetic and real LR images.
Accurate Blur Models vs. Image Priors in Single Image Super-resolution
TLDR
It is found that an accurate blur model is more important than a sophisticated image prior in reconstructing raw lowers images acquired by an actual camera and the default blur models of various SR algorithms may differ from the camera blur, typically leading to over-smoothed results.
Example-Based Super-Resolution
TLDR
This work built on another training-based super- resolution algorithm and developed a faster and simpler algorithm for one-pass super-resolution that requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data.
Fast Image Super-Resolution Based on In-Place Example Regression
We propose a fast regression model for practical single image super-resolution based on in-place examples, by leveraging two fundamental super-resolution approaches- learning from an external
...
...