Current Issue Cover

邸维巍, 张旭东, 胡良梅, 段琳琳(合肥工业大学计算机与信息学院图像信息处理研究室, 合肥 230009)

摘 要
目的 针对深度图像分辨率非常低的问题,结合同场景高分辨率彩色图像,提出一种基于彩色图约束的二阶广义总变分深度图超分辨率重建方法。方法 首先将低分辨率深度图映射到高分辨率彩色空间;然后利用二阶广义总变分模型,将带有边缘指示函数的高分辨率彩色约束项作为正则项,使得深度图像超分辨率重建问题变成最优求解问题;最后通过迭代重加权和原—对偶方法进行求解。结果 实验结果表明,本文方法可以有效地保护图像的边缘结构,在定性和定量两个方面都可达到很好的效果。结论 本文方法可以有效地解决深度图分辨率非常低的问题。
Depth image super-resolution based on second-order total generalized variation constrained by color image

Di Weiwei, Zhang Xudong, Hu Liangmei, Duan Linlin(Laboratory of Image Information Processing, School of Computer and Information, Hefei University of Technology, Hefei 230009, China)

Objective The resolution of depth image is very low. In this paper, with a registered and potentially high resolution color image of the same scene, we propose a second order total generalized variation super-resolution method based on color image regularization terms. Method First, the low-resolution depth image is mapped onto the high-resolution color image coordinate system. Then, the second-order total generalized variation model is used and the high-resolution image constrained term with an edge indicator function is used to construct the regularization term. The depth map super-resolution problem is solved by developing an energy optimization framework. Finally, the reweighted method and primal-dual method are used to solve the energy function. Result The experimental results demonstrate that the proposed approach can well preserve the edge information and obtain a high resolution depth image in terms of both its spatial resolution and depth precision. Conclusion The proposed method can effectively solve the problem of low depth image resolution.