期刊文献+

基于逆向映射的空洞填补方法 被引量:1

An approach of holes filling based on backward warping
原文传递
导出
摘要 为了有效填补虚拟视点图像中的公共空洞,提出了一种基于逆向映射的空洞填补方法。首先利用深度图像绘制(DIBR)技术将左、右参考视点映射到虚拟视点位置,利用图像膨胀方法将映射的虚拟视图中的空洞区域进行扩大,以消除虚拟视点图像中的伪影瑕疵;然后,提取出膨胀后空洞区域的边界,并将其逆映射到原始的参考图像中,根据空洞与边界的相对位置,选取原始图像中相对位置上的像素来填充虚拟视图中的空洞区域;最后,将空洞填补之后的左、右视点映射的虚拟视图进行融合获得最终的虚拟视图。实验证明,本文方法有效解决了传统空洞填补方法容易将前景像素填充到背景区域的问题,能够获得较好的视觉观看效果和较高的客观峰值信噪比(PSNR)值。 In order to effectively fill the common holes in the virtual view imag e,we propose a novel approach of holes filling based on the backward 3D image warping method.In this method, first,the left reference view and right reference view are warped to the virtual view position with the t echnology of 3D image warping and the corresponding depth map information,respectively.To eliminate the ghosting art ifacts in the virtual view image, we enlarge the holes region in the warped virtual views with image dilating meth od.Second,the boundary of holes region is obtained and then backward warped to the original left and ri ght reference views with 3D image warping.Based on the relative position between holes and boundary,the c orresponding pixels in the reference views are chosen to fill the holes in the warped virtual views.Finally ,the holes filled warped virtual views are blended,and the final virtual image is obtained.Experimen tal results show that the proposed method can effectively solve the problem of filling foreground pixels into the b ackground areas with the traditional neighborhood interpolation method and image in-painting method.The proposed me thod also can obtain better subjective visual effects and achieve higher objective peak signal-to-noise ratio.
作者 王来花 齐苏敏 王玉田 倪建成 陈华 WANG Lai-hua 1, QI Su-min1 , WANG Yu-tian1 , NI Jian-cheng1 , CHEN Hua2(1. School of Software, Qufu Normal University, Qufu 273165, China ; 2. School of Information Science and Engi neering, Ningbo University, Ningbo 315211 ,Chin)
出处 《光电子.激光》 EI CAS CSCD 北大核心 2018年第3期318-324,共7页 Journal of Optoelectronics·Laser
基金 国家自然科学基金青年基金(61601261) 山东省自然科学基金博士基金(ZR2016FB20)资助项目
关键词 深度图像点绘制(DIBR) 3D图像映射 图像融合 图像膨胀 空洞填补 depth-image-based rendering (DIBR) 3D warping image blending image dilating holes filling
  • 相关文献

参考文献4

二级参考文献63

  • 1刘苏醒,安平,宓桃,张兆杨.自由视点视频系统中虚拟视合成及校正方法[J].光电子.激光,2009,20(9):1234-1237. 被引量:3
  • 2Smolic A, Mueller K, Merkle P, et al. Multi-view video plus depth (MVD) format for advanced 3D video systems[R]. ITUT and ISO/IEC JTC1 ,JVT-W100,San Jose,USA. Apr,2007.
  • 3Tanimoto M. Overview of free viewpoint television[J]. Signal Processing: Image Communication,2006,21(6) :454-461.
  • 4Krishnamurthy R, Tao H, Chai B B, et al. Compression and transmission of depth maps for image-based rendering[A]. In: Proceedings of International Conference on Image Processing [C]. 2001,3 : 828-831.
  • 5Tanimoto M, Fujii T, Suzuki K, et al. Multi-view depth map of rena and akko & kayo[R].ISO/IEC JTC1/SC29/ WG11, MPEG-M14888, Shenzhen, China, Oct, 2007.
  • 6Kauff P,Atzpadin N,Fehn C,et al. Depth map creation and image based rendering for advanced 3-D TV Services Providing Interoperability and Scalability[J].Signal Processing: Image Communication, 2007,22 (2) :217-234.
  • 7Daribo I,Tillier C, Pesquet-Popescu B. Adaptive wavelet coding of the depth map for stereoscopic view synthesis[A]. IEEE lOth Workshop on Multimedia Signal Processing[C]. 2008.413-417.
  • 8Morvan Y, Farin D,et al. Depth-image compression based on an R-D optimized quadtree decomposition for the transmission of multi-view images[J]. IEEE Transactions on Consumer Electronics, 2007:105-108.
  • 9Merkle P, Smolic A, Mueller K,et al. MVC, Experiments on coding of multi-view video plus depth. JVT-X064, Geneva, CH, 2007.
  • 10Oh H,Ho Y S. H. 264-based depth map sequence coding using motion information of corresponding texture video[J]. Lecture Notes in Computer Science, 2006,4319 : 898-907.

共引文献20

同被引文献10

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部