Loughborough University
Browse
neucom22.pdf (3.3 MB)

A neural refinement network for single image view synthesis

Download (3.3 MB)
journal contribution
posted on 2022-05-23, 09:06 authored by Lei Jiang, Haibin CaiHaibin Cai, Gerald SchaeferGerald Schaefer, Qinggang MengQinggang Meng

Recent years have seen an increasing interest in single image view synthesis. It remains however a challenging task due to the lack of comprehensive colour and depth information from different views. In this paper, we propose a novel view synthesis approach that incorporates a Neural Image Refinement Network (NIRN) and generates both depth and colour images for the target view in an end-to-end manner. The appearance of the colour image greatly benefits from the generated depth image as it provides an intermediate projection relationship for the object in the 3D world. Since the direct application of geometric projection mapping will result in empty regions and/or distortions, our approach proposes to embed a novel refinement network into the view synthesis pipeline for improved performance. Experimental results on three publicly available datasets demonstrate that our NIRN outperforms other state-of-the-art view synthesis methods.

Funding

EPSRC Centre for Doctoral Training in Embedded Intelligence

Engineering and Physical Sciences Research Council

Find out more...

SukeIntel Co., Ltd

History

School

  • Science

Department

  • Computer Science

Published in

Neurocomputing

Volume

496

Pages

35 - 45

Publisher

Elsevier

Version

  • AM (Accepted Manuscript)

Rights holder

© Elsevier

Publisher statement

This paper was accepted for publication in the journal Neurocomputing and the definitive published version is available at https://doi.org/10.1016/j.neucom.2022.04.123

Acceptance date

2022-04-24

Publication date

2022-04-28

Copyright date

2022

ISSN

0925-2312

Language

  • en

Depositor

Dr Haibin Cai. Deposit date: 20 May 2022

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC