arrow
返回

Computational Multi-View Imaging with Kinect

delete2014-09-01
delete15
PRE
AI
X
Xinchen Ye
杨敬钰 封面图
杨敬钰 (Jingyu Yang) *
H
Hao Huang
C
Chunping Hou
Y
Yao Wang
DOI:10.1109/TBC.2014.2345931delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
The lack of 3-D content has become a bottleneck for the advancement of three-dimensional television (3-DTV), but conventional multicamera arrays for multiview imaging are expensive to setup and cumbersome to use. This paper proposes a lightweight multiview imaging approach with Kinect, a handheld integrated depth-color camera, under the depth-image-based rendering framework. The proposed method consists of two components: depth restoration from noisy and incomplete depth measurements and view synthesis from depth-color pairs. In depth restoration, we propose a moving 2-D polynomial approximation via least squares to suppress quantization errors in the acquired depth values, and propose a progressive edge-guided trilateral filter to fill missing areas of the depth map. Edges extracted from color image are used to predict the locations of depth discontinuities in missing areas and to guide the proposed trilateral filter avoiding filtering across discontinuities. In view synthesis, we propose a low-rank matrix restoration model to inpaint disocclusion regions, fully exploiting the nonlocal correlations in images, and devise an efficient algorithm under the augmented lagrange multiplier (ALM) framework. Disocclusion areas are inpainted progressively from the boundaries of disocclusion with an estimated priority consisting of four terms: warping term, reliability term, texture term, and depth term. Experimental results show that our method restores high quality depth maps even for large missing areas, and synthesizes natural multiview images from restored depth maps. Strong 3-D visual experiences are observed when the synthesized multiview images are shown in two types of stereoscopic displays.
Keyword:
Multiview imaging
Kinect
depth restoration
matrix completion
view synthesis
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Broadcasting 封面图
IEEE Transactions on Broadcasting
IF:
4.8
论文数:
2.1K
被引数:
3.0K

机构

T
tianjin university
学者数:
8.0W
论文数: 5.8W
被引数: 88
N
New York University
学者数:
4.4W
论文数: 3.9W
被引数: 5.8W
引用论文

引用论文

Local and Systemic Effects of Immune Checkpoint Blockade on Relapsed Myeloid Malignancies Following Allogeneic Hematopoietic Stem Cell Transplantation
err2020-11-05
err0
errOAAI
errLivius Penter; Yi Zhang; Alexandra Savell; Srinika Ranasinghe; Teddy Huang; Nicoletta Cieri; Satyen H Gohil; Wandi Zhang; Shuqiang Li; Robert Zeiser; Haesook T. Kim; Kenneth J. Livak; Jerome Ritz; Donna S. Neuberg; Robert J. Soiffer; X. Shirley Liu; Matthew S. Davids; Pavan Bachireddy; Catherine J. Wu
err分享
err收藏
Growth Rate of Pulmonary Metastases from Soft Tissue Sarcoma
err2009-07-08
err0
errOAAI
errB. Rööser; H. Pettersson; T. Alvegård
err分享
err收藏
Embedded Generation
err
IF0
err2000-01-01
err0
PREAI
errN. Jenkins; et al.
err分享
err收藏
3D-TV Content Storage and Transmission
err2011-06-01
err108
errOAAI
errVetro, Anthony; Tourapis, Alexis M.; Mueller, Karsten; Chen, Tao
err分享
err收藏
Flame Retardant Property of Sb2O3/SnO2 and their Synergism in Flexible PVC
err2006-05-01
err0
PREAI
errHai Wang; Hua Wang; Zhansheng Guo; Shuangchun Qi; Chunming Tian
err分享
err收藏
A Service-Agnostic Software Framework for Fast and Efficient in-Kernel Network Services
err2019-09-01
err0
errOAAI
errSebastiano Miano; Matteo Bertrone; Fulvio Risso; Mauricio Vasquez Bernal; Yunsong Lu; Jianwen Pi; Aasif Shaikh
err分享
err收藏
学者 查看更多内容