摘要
深度相机在最近几年越来越流行,然而受限于设备,通过深度相机获取的深度图像分辨率不高。文章提出了一种新的方法来提高这类图像的分辨率。首先通过细分模型构建目标分辨率图像的边界图,并通过“节点压缩算法”生成光滑的边界图;其次在该边界图的基础上,利用改进的联合双边滤波来重建高分辨率深度图像。该文提出的方法不仅降低了边界的锯齿现象,且具有良好的保形性。实验结果表明,该方法优于经典的方法。
Consumer depth cameras have become more and more popular in recent years. However, limited by devices, the resolution generated by the cameras is not satisfactory. In this paper, a novel method independent of the external information is presented to upscale the low resolution depth images. The generation of upscaled depth image is guided by the edge map, which is constructed by the subdivision scheme, and the node compression method is used to overcome the zigzag artifacts in edge. Then, a modified joint bilateral filter is adopted to reconstruct the high resolution depth image with the guidance of the edge map, by which jagged artifacts can be reduced and sharp edges can be preserved well. Experimental results show that the proposed method outperforms the state-of-the-art super resolution reconstruction methods both qualitatively and quantitatively.
作者
黄廉珂
檀结庆
何蕾
彭凯军
HUANG Lianke;TAN Jieqing;HE Lei;PENG Kaijun(School of Mathematics,Hefei University of Technology,Hefei 230601,China)
出处
《合肥工业大学学报（自然科学版）》
CAS
北大核心
2019年第8期1142-1148,共7页
Journal of Hefei University of Technology：Natural Science
基金
国家自然科学基金资助项目(61070227
61472466
61672202
61502141)
关键词
深度图像
超分辨率
细分模型
联合双边滤波
depth image
super resolution
subdivision scheme
joint bilateral filter
