标题:Virtual View Synthesis Based on DIBR and Image Inpainting
作者:Gao, Yuhan; Chen, Hui; Gao, Weisong; Vaudrey, Tobi
作者机构:[Gao, Yuhan; Chen, Hui] Shandong Univ, Sch Informat Sci & Engn, Jinan 250100, Shandong, Peoples R China.; [Gao, Weisong] Multimedia R&D Ctr, Qingdao 更多
会议名称:6th Pacific-Rim Symposium on Image and Video Technology (PSIVT)
会议日期:OCT 28-NOV 01, 2013
来源:IMAGE AND VIDEO TECHNOLOGY, PSIVT 2013
出版年:2014
卷:8333
页码:172-183
DOI:10.1007/978-3-642-53842-1_15
关键词:Virtual View Synthesis; Depth-Image-Based-Rendering (DIBR); Image; Inpainting; Interpolation
摘要:In 3DTV research, virtual view synthesis is a key component to the technology. Depth-image-based-rendering (DIBR) is an important method to realize virtual view synthesis. However, DIBR always results in hole problems where the depth and colour values are not known. Hole-filling methods often cause other problems, such as edge-ghosting and cracks. This paper proposes an algorithm that uses the depth and colour images to address the holes. It exploits the assumption of a virtual view between two laterally aligned reference cameras. The hole-filling method is performed on the blended depth image by morphological operations, and inpainting of the holes is obtained with the position information provided by the filtered depth maps. A new interpolation method to eliminate edge-ghosting is also presented, which additionally uses a post-processing technique to improve image quality. The main novelty of this paper is the unique image blending, which is more efficient than preprocessing depth maps. It is also the first method that is using morphological closing in the depth map de-noising process. The method proposed in this paper can effectively remove holes and edge-ghosting. Experimental quantitative and qualitative results show the proposed algorithm improves quality dramatically on traditional methods.
收录类别:CPCI-S;EI;SCOPUS
WOS核心被引频次:1
Scopus被引频次:1
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-s2.0-84958520626&doi=10.1007%2f978-3-642-53842-1_15&partnerID=40&md5=4a4695930e29b1732c7d3356a73f0239
TOP