标题:A DIBR method based on inverse mapping and depth-aided image inpainting
作者:Cheng, Cong ;Liu, Ju ;Yuan, Hui ;Yang, Xiaohui ;Liu, Wei
作者机构:[Cheng, Cong ;Liu, Ju ;Yuan, Hui ;Yang, Xiaohui ] School of Information Science and Engineering, Shandong University, Jinan, China;[Liu, Ju ;Liu, Wei 更多
会议名称:2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013
会议日期:6 July 2013 through 10 July 2013
来源:2013 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013 - Proceedings
出版年:2013
页码:518-522
DOI:10.1109/ChinaSIP.2013.6625394
关键词:3DV; depth image based rendering; image inpainting; inverse mapping; view synthesis
摘要:Depth-image-based rendering (DIBR) has attracted more and more attention as a method of virtual view rendering in three-dimensional video (3DV) applications. Many efforts have been dedicated to realize high-quality rendering, ranging from pre-process of the reference depth images to post-process of the virtual texture images. A DIBR method based on inverse mapping and depth-aided image inpainting technique is proposed in this paper. In the proposed method, inverse mapping rendering technique is adopted to realize the 3D warping instead of traditional forward mapping; and a modified image inpainting technique in which depth information is considered is employed to inpaint the disocclusion regions. Besides, morphological processing is performed on the reference depth image to avoid the artifacts along the disocclusion areas. Experimental results demonstrate that the proposed method can obtain higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) in comparison to the previous methods, while producing satisfactory visual effect. © 2013 IEEE.
收录类别:EI;SCOPUS
Scopus被引频次:2
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84889566110&doi=10.1109%2fChinaSIP.2013.6625394&partnerID=40&md5=16784944508aa9d255fc7ae9dd24df9c
TOP