Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond
MD Raqib Khan, Anshul Negi, Ashutosh Kulkarni, Shruti S. Phutke,, Santosh Kumar Vipparthi, Subrahmanyam Murala

TL;DR
Phaseformer introduces a lightweight, phase-based transformer network that significantly improves underwater image restoration and low-light enhancement by effectively extracting features and restoring structural details, outperforming existing methods.
Contribution
The paper presents a novel phase-based self-attention mechanism within a lightweight transformer for underwater image restoration and low-light enhancement, with extensive validation on multiple datasets.
Findings
Outperforms state-of-the-art methods in underwater image restoration
Effective in low-light image enhancement tasks
Uses only 1.77M parameters, demonstrating efficiency
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Signal Denoising Methods · Image Enhancement Techniques · Advanced Image Fusion Techniques
MethodsSoftmax · Attention Is All You Need
