联合双边图像插值

Joint bilateral image interpolation

传统的图像插值算法及其改进算法都存在边缘模糊、边缘锯齿或局部扭曲变形等问题。提出联合双边图像插值,首先采用传统插值算法对原始图像进行插值,将其结果作为导引图像对原始图像进行联合双边上采样,并给出其核函数方差的自适应确定算法。实验结果表明,与传统插值算法相比,该算法明显改进插值图像质量,与已有的绝大多数非线性改进算法相比还提高了插值速度。

Conventional improved interpolation introduces blurs, jagged edges, or artifacts. The Joint Bilateral Interpolation （JBI） is proposed in this paper. The low-resolution （LR） input image is first being interpolated with a fast and simple algorithm and then the interpolated result is used as a guidance image to apply the joint bilateral filter to upsample the LR image. And the parameters of Gaussian kernel function are given in the paper. Experiment results demonstrate that our new interpolation algorithm substantially improves the quality of the interpolated images and costs less calculation time than most existing nonlinear improved interpolation algorithms.