eprintid: 3454
rev_number: 9
eprint_status: archive
userid: 311
dir: disk0/00/00/34/54
datestamp: 2019-05-27 08:29:52
lastmod: 2019-06-03 04:11:31
status_changed: 2019-05-27 08:29:52
type: article
metadata_visibility: show
creators_name: Dinh, Trieu Duong
creators_name: Le Dinh, Minh
creators_name: Byeungwoo, Jeon
creators_name: Hoang, Van Xiem
creators_id: duongdt@vnu.edu.vn
creators_id: minhle2994@gmail.com
creators_id: bjeon@skku.edu
creators_id: xiemhoang@vnu.edu.vn
title: A Novel Fusion Method for 3D-TV View Synthesis Using Temporal and Disparity Correlations
ispublished: submitted
subjects: ECE
subjects: IT
subjects: Scopus
divisions: fac_fet
abstract: View synthesis like Depth-image-based-rendering (DIBR) plays a significant role in 3D content creation for 3D-TV. However, perceptual errors introduced by current view synthesis often result in severe distortions in synthesized images. In this paper, we propose a novel view synthesis fusion (VSF) method which adaptively exploits temporal and disparity correlations to improve the quality of the synthesized picture. The proposed VSF method defines a robust correlation assessment metric for fusing several pre-created virtual view candidates. Unlike conventional methods, the proposed fusion algorithm is applied for both hole and non-hole areas. Experimental results show significantly outperforming peak signal-to noise ratio (PSNR) and subjective visual quality by the proposed method compared to other conventional methods.
date: 2019
date_type: submitted
publisher: The Institute of Electronics and Information Engineers (IEIE)
official_url: http://www.ieiespc.org/
full_text_status: public
publication: IEIE Trans. on Smart Processing and Computing
refereed: TRUE
issn: 2287-5255
funders: Vietnam National University, Hanoi (VNU)
projects: Project No. QG. 17. 42.
citation:   Dinh, Trieu Duong and Le Dinh, Minh and Byeungwoo, Jeon and Hoang, Van Xiem  (2019) A Novel Fusion Method for 3D-TV View Synthesis Using Temporal and Disparity Correlations.  IEIE Trans. on Smart Processing and Computing .    ISSN 2287-5255    (Submitted)  
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3454/1/_system_appendPDF_proof_hi_2pages.pdf