Loading…

Enhancement-Registration-Homogenization (ERH): A Comprehensive Underwater Visual Reconstruction Paradigm

This paper presents a comprehensive underwater visual reconstruction paradigm that comprises three procedures, i.e., the E-procedure, the R-procedure, and the H-procedure. The E-procedure enhance enhance s original underwater images based on color compensation balance and weighted image fusion, yiel...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2022-10, Vol.44 (10), p.6953-6967
Main Authors: Song, Huajun, Chang, Laibin, Chen, Ziwei, Ren, Peng
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a comprehensive underwater visual reconstruction paradigm that comprises three procedures, i.e., the E-procedure, the R-procedure, and the H-procedure. The E-procedure enhance enhance s original underwater images based on color compensation balance and weighted image fusion, yielding restored color, sharpened edges, and global contrast. The R-procedure register register s multiple enhanced underwater images by exploiting global similarity and local deformation. The H-procedure homogenize homogenize s the registered underwater images by multi-scale composition strategy, which eliminates the inhomogeneous transition and brightness difference across overlapping regions, resulting in a reconstructed wide-field underwater image with comfortable and natural visibility. The three procedures operate in a cascade where the former procedure processes underwater images in a way that facilitates the latter one. We refer to the overall three procedures as the Enhancement-Registration-Homogenization (ERH) paradigm. Comprehensive qualitative and quantitative empirical evaluations reveal that our ERH paradigm outperforms state-of-the-art visual reconstruction methods, including the AutoStitch, APAP, SPHP, APNAP, and REW.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2021.3097804