Iterative projection reconstruction for fast and efficient image upsampling

Iterative projection reconstruction for fast and efficient image upsampling
复制标题

DOI:
10.1016/j.neucom.2016.11.049
复制
发表时间:
2017-02
期刊:
影响因子:
6
通讯作者:
Yang Zhao;Ronggang Wang;Wei Jia;Wenmin Wang;Wen Gao
Yang Zhao;Ronggang Wang;Wei Jia;Wenmin Wang;Wen Gao
中科院分区:
计算机科学2区
文献类型:
--
作者:
Yang Zhao;Ronggang Wang;Wei Jia;Wenmin Wang;Wen Gao

文献摘要

被引文献

相似文献

随着超高分辨率显示设备的发展,精细纹理细节的视觉感知变得越来越重要。传统的图像上采样方法要么丢失了高频纹理细节,要么时间开销很大。在本文中,我们提出了一种迭代投影重建(IPR)方法快速和有效的图像上采样。该方法通过迭代投影过程来细化高频纹理细节,并利用预先计算的投影矩阵来加速基于实例的图像重建。结果表明,该方法能够以较低的时间代价再现纹理细节。实验结果表明,该方法优于一些国家的最先进的方法。
With the development of ultra-high-resolution display devices, the visual perception of fine texture details is becoming increasingly important. Traditional image upsampling methods suffer from either loss of high-frequency texture details or very high time cost. In this paper, we propose an iterative projection reconstruction (IPR) method for fast and efficient image upsampling. The proposed method refines high-frequency texture details with an iterative projection process, and utilizes the pre-computed projection matrix to accelerate the example-based image reconstruction. As a result, the proposed method can reproduce fine texture details with low time cost. Experimental results demonstrate that the proposed method outperforms some state-of-the-art methods.