Saved in:
Bibliographic Details
Main Authors: Khan, MD Raqib, Negi, Anshul, Kulkarni, Ashutosh, Phutke, Shruti S., Vipparthi, Santosh Kumar, Murala, Subrahmanyam
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.01456
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916502983147520
author Khan, MD Raqib
Negi, Anshul
Kulkarni, Ashutosh
Phutke, Shruti S.
Vipparthi, Santosh Kumar
Murala, Subrahmanyam
author_facet Khan, MD Raqib
Negi, Anshul
Kulkarni, Ashutosh
Phutke, Shruti S.
Vipparthi, Santosh Kumar
Murala, Subrahmanyam
contents Quality degradation is observed in underwater images due to the effects of light refraction and absorption by water, leading to issues like color cast, haziness, and limited visibility. This degradation negatively affects the performance of autonomous underwater vehicles used in marine applications. To address these challenges, we propose a lightweight phase-based transformer network with 1.77M parameters for underwater image restoration (UIR). Our approach focuses on effectively extracting non-contaminated features using a phase-based self-attention mechanism. We also introduce an optimized phase attention block to restore structural information by propagating prominent attentive features from the input. We evaluate our method on both synthetic (UIEB, UFO-120) and real-world (UIEB, U45, UCCS, SQUID) underwater image datasets. Additionally, we demonstrate its effectiveness for low-light image enhancement using the LOL dataset. Through extensive ablation studies and comparative analysis, it is clear that the proposed approach outperforms existing state-of-the-art (SOTA) methods.
format Preprint
id arxiv_https___arxiv_org_abs_2412_01456
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond
Khan, MD Raqib
Negi, Anshul
Kulkarni, Ashutosh
Phutke, Shruti S.
Vipparthi, Santosh Kumar
Murala, Subrahmanyam
Computer Vision and Pattern Recognition
Image and Video Processing
Quality degradation is observed in underwater images due to the effects of light refraction and absorption by water, leading to issues like color cast, haziness, and limited visibility. This degradation negatively affects the performance of autonomous underwater vehicles used in marine applications. To address these challenges, we propose a lightweight phase-based transformer network with 1.77M parameters for underwater image restoration (UIR). Our approach focuses on effectively extracting non-contaminated features using a phase-based self-attention mechanism. We also introduce an optimized phase attention block to restore structural information by propagating prominent attentive features from the input. We evaluate our method on both synthetic (UIEB, UFO-120) and real-world (UIEB, U45, UCCS, SQUID) underwater image datasets. Additionally, we demonstrate its effectiveness for low-light image enhancement using the LOL dataset. Through extensive ablation studies and comparative analysis, it is clear that the proposed approach outperforms existing state-of-the-art (SOTA) methods.
title Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2412.01456