Single-image super-resolution based on local biquadratic spline with edge constraints and adaptive optimization in trans
- PDF / 2,763,835 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 55 Downloads / 167 Views
ORIGINAL ARTICLE
Single-image super-resolution based on local biquadratic spline with edge constraints and adaptive optimization in transform domain Danya Zhou1
· Yepeng Liu2 · Xuemei Li2,3 · Caiming Zhang2,3
Accepted: 20 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract This paper proposes a novel single-image super-resolution method based on local biquadratic spline with edge constraints and adaptive optimization in transform domain. The complex internal structure of the image makes the values of adjacent pixels often differ greatly. Using surface patches to interpolate image blocks can avoid large surface oscillation. Because the quadratic spline has better shape-preserving property, we construct the biquadratic spline surface on each image block to make the interpolation more flexible. The boundary conditions have great influence on the shape of local biquadratic spline surfaces and are the keys to constructing surfaces. Using edge information as a constraint to calculate them can reduce jagged and mosaic effects. To decrease the errors caused by surface fitting, we propose a new adaptive optimization model in transform domain. Compared with the traditional iterative back-projection, this model further improves the magnification accuracy by introducing SVD-based adaptive optimization. In the optimization, we convert similar block matrices to the transform domain by SVD. Then the contraction coefficients are calculated according to the non-local self-similarity, and the singular values are contracted. Experimental comparison with the other state-of-the-art methods shows that the proposed method has better performance in both visual effect and quantitative measurement. Keywords Local biquadratic spline · Boundary conditions · Singular value contraction · Adaptive optimization
1 Introduction The purpose of single-image super-resolution (SISR) is to recover high-frequency information from the low-resolution (LR) input images and generate reasonable high-resolution (HR) images that are not conflict with the LR versions. SISR is an important branch of image processing and has applications in many areas, such as medical imaging, security surveillance, satellite imagery, e-commerce and many others. There are two main types of SISR methods: interpolationbased methods and learning-based methods.
B
Xuemei Li [email protected] Danya Zhou [email protected]
1
School of Computer Science and Technology, Shandong University, Jinan, China
2
School of Software, Shandong University, Jinan, China
3
Shandong Co-Innovation Center of Future Intelligent Computing, Yantai, China
Classical polynomial interpolation methods [21–23] are extensively used due to their simplicity and speed of computation. However, since these methods use the commonly used polynomial fitting method to construct the interpolation surface of the image, the generated images are often too smooth and appear jagged and ringing effects in texture and edge areas. To solve this problem, some edge-oriented interpolation metho
Data Loading...