This paper presents a new hole-filling method that uses extrapolated spatio-temporal background information to obtain a synthesized free-view. A new background codebook for extracting reliable temporal background information is introduced. In addition, the paper addresses estimating spatial local background to distinguish background and foreground regions so that spatial background information can be extrapolated. Background holes are filled by combining spatial and temporal background information. Finally, exemplar-based inpainting is applied to fill in the remaining holes using a new priority function. The experimental results demonstrated that satisfactory synthesized views can be obtained using the proposed algorithm.
Huu-Noi DOAN
Soongsil University
Tien-Dat NGUYEN
Soongsil University
Min-Cheol HONG
Soongsil University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Huu-Noi DOAN, Tien-Dat NGUYEN, Min-Cheol HONG, "Hole-Filling Algorithm with Spatio-Temporal Background Information for View Synthesis" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 9, pp. 1994-2004, September 2017, doi: 10.1587/transinf.2016PCP0010.
Abstract: This paper presents a new hole-filling method that uses extrapolated spatio-temporal background information to obtain a synthesized free-view. A new background codebook for extracting reliable temporal background information is introduced. In addition, the paper addresses estimating spatial local background to distinguish background and foreground regions so that spatial background information can be extrapolated. Background holes are filled by combining spatial and temporal background information. Finally, exemplar-based inpainting is applied to fill in the remaining holes using a new priority function. The experimental results demonstrated that satisfactory synthesized views can be obtained using the proposed algorithm.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016PCP0010/_p
Copy
@ARTICLE{e100-d_9_1994,
author={Huu-Noi DOAN, Tien-Dat NGUYEN, Min-Cheol HONG, },
journal={IEICE TRANSACTIONS on Information},
title={Hole-Filling Algorithm with Spatio-Temporal Background Information for View Synthesis},
year={2017},
volume={E100-D},
number={9},
pages={1994-2004},
abstract={This paper presents a new hole-filling method that uses extrapolated spatio-temporal background information to obtain a synthesized free-view. A new background codebook for extracting reliable temporal background information is introduced. In addition, the paper addresses estimating spatial local background to distinguish background and foreground regions so that spatial background information can be extrapolated. Background holes are filled by combining spatial and temporal background information. Finally, exemplar-based inpainting is applied to fill in the remaining holes using a new priority function. The experimental results demonstrated that satisfactory synthesized views can be obtained using the proposed algorithm.},
keywords={},
doi={10.1587/transinf.2016PCP0010},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Hole-Filling Algorithm with Spatio-Temporal Background Information for View Synthesis
T2 - IEICE TRANSACTIONS on Information
SP - 1994
EP - 2004
AU - Huu-Noi DOAN
AU - Tien-Dat NGUYEN
AU - Min-Cheol HONG
PY - 2017
DO - 10.1587/transinf.2016PCP0010
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2017
AB - This paper presents a new hole-filling method that uses extrapolated spatio-temporal background information to obtain a synthesized free-view. A new background codebook for extracting reliable temporal background information is introduced. In addition, the paper addresses estimating spatial local background to distinguish background and foreground regions so that spatial background information can be extrapolated. Background holes are filled by combining spatial and temporal background information. Finally, exemplar-based inpainting is applied to fill in the remaining holes using a new priority function. The experimental results demonstrated that satisfactory synthesized views can be obtained using the proposed algorithm.
ER -