Physics Informed Capsule Enhanced Variational AutoEncoder for Underwater Image Enhancement

arXiv (Cornell University)

Abstract

We present a novel dual-stream architecture that achieves state-of-the-art underwater image enhancement by explicitly integrating the Jaffe-McGlamery physical model with capsule clustering-based feature representation learning. Our method simultaneously estimates transmission maps and spatially-varying background light through a dedicated physics estimator while extracting entity-level features via capsule clustering in a parallel stream. This physics-guided approach enables parameter-free enhancement that respects underwater formation constraints while preserving semantic structures and fine-grained details. Our approach also features a novel optimization objective ensuring both physical adherence and perceptual quality across multiple spatial frequencies. To validate our approach, we conducted extensive experiments across six challenging benchmarks. Results demonstrate consistent improvements of $+0.5$dB PSNR over the best existing methods while requiring only one-third of their computational complexity (FLOPs), or alternatively, more than $+1$dB PSNR improvement when compared to methods with similar computational budgets. Code and data \textit{will} be available at https://github.com/iN1k1/.

Authors 2

1. Niki Martinel

   University of Udine

   Affiliation as printed

   Department of Mathematics, Computer Science and Physics , University of Udine , Via Delle Scienze 206 , Udine , 33100 , Italy

2. Rita Pucci Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science , University of Leiden , Einsteinweg 55 , Leiden , 2333 , The Netherlands