2016
DOI: 10.1016/j.ins.2016.02.015
|View full text |Cite
|
Sign up to set email alerts
|

Single image super-resolution by approximated Heaviside functions

Abstract: Image super-resolution is a process to enhance image resolution. It is widely used in medical imaging, satellite imaging, target recognition, etc. In this paper, we conduct continuous modeling and assume that the unknown image intensity function is defined on a continuous domain and belongs to a space with a redundant basis. We propose a new iterative model for single image super-resolution based on an observation: an image is consisted of smooth components and non-smooth components, and we use two classes of … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
30
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
6
2

Relationship

2
6

Authors

Journals

citations
Cited by 37 publications
(30 citation statements)
references
References 63 publications
0
30
0
Order By: Relevance
“…ScSR [20] is not compared here because it requires HR images for training. AHF [4] approach is not sparse coding method and needs Table 1. The PSNR (dB) results obtained through the experiments, HFSR is the proposed method with conventional refinement, while HFSR(multi-scale) is the proposed method with multi-scale Refinement.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…ScSR [20] is not compared here because it requires HR images for training. AHF [4] approach is not sparse coding method and needs Table 1. The PSNR (dB) results obtained through the experiments, HFSR is the proposed method with conventional refinement, while HFSR(multi-scale) is the proposed method with multi-scale Refinement.…”
Section: Resultsmentioning
confidence: 99%
“…However, SR is an ill-posed issue which is very difficult to obtain the optimal solution. The approaches for SISR can be divided into three categories including interpolation-based methods [22,4,11,16,3], reconstruction-based methods [2,18,6,7,9], and learning-based methods [10,12,20,5,17,15]. Reconstruction-based methods and learning-based methods often yield more accurate results than interpolation-based algorithm, since those methods can acquire more information from statistical prior and external data even though more time-consuming.…”
Section: Introductionmentioning
confidence: 99%
“…We can distinguish between Multiple-Image Super-resolution (MISR) and Single Image Superresolution (SISR). SISR [30] allows to obtain a HR image from only one observed LR image by applying, for instance, interpolation [31][32][33][34] or machine learning techniques based on LR/HR image patches [35][36][37][38][39], see [40] for the use of deep learning techniques in image recovery problems. However, when a video sequence or a set of LR images is available, MISR is preferred.…”
Section: State-of-the-artmentioning
confidence: 99%
“…So it is more intuitive to consider the correlation of different patches. From another aspect, patch is successfully used in the field of image processing recently, not only face recognition [1416] but also image denoising [1719], image superresolution [20, 21], and image decomposition (cartoon-texture [22, 23] or illumination-reflectance [24] and further retinex image enhancement [25]). Patch is becoming a basic tool in these above-mentioned literatures.…”
Section: Introductionmentioning
confidence: 99%