# Physics-Guided Spectral Distillation for Underwater Image Enhancement on Resource-Constrained Devices

arXiv: https://arxiv.org/abs/2609.34795 · HTML: https://mlsanity.com/paper/2609.34795/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration](https://mlsanity.com/paper/2311.16845/) (2023)
- [Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model](https://mlsanity.com/paper/2311.11638/) (2023)
- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)
- [Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation](https://mlsanity.com/paper/2203.06321/) (2022)
- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [FreeKD: Knowledge Distillation via Semantic Frequency Prompt](https://mlsanity.com/paper/2311.12079/) (2023)
- [Frequency Attention for Knowledge Distillation](https://mlsanity.com/paper/2403.05894/) (2024)
- [A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing](https://mlsanity.com/paper/2003.01446/) (2020)
- [A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement](https://mlsanity.com/paper/2308.05447/) (2023)
- [Meta-Learning based Degradation Representation for Blind Super-Resolution](https://mlsanity.com/paper/2207.13963/) (2022)
- [Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration](https://mlsanity.com/paper/2412.08939/) (2024)
- [Adaptive Dual-domain Learning for Underwater Image Enhancement](https://mlsanity.com/paper/2504.19198/) (2025)
- [CPDM: Content-Preserving Diffusion Model for Underwater Image Enhancement](https://mlsanity.com/paper/2401.15649/) (2024)

## Abstract (arXiv)

Underwater image enhancement is crucial for improving visual perception in marine applications. Existing underwater image enhancement studies mainly focus on enhancement quality and visual fidelity, while rarely considering real-time deployment capability, which is essential for resource-constrained underwater robots. To this end, we introduce a physics-guided spectral distillation (PSD) method, which reduces model capacity for real-time applications while maintaining the high performance of underwater image enhancement models. To decompose the outputs of teacher and student models, PSD adopts a multilevel Haar discrete wavelet transform. It transfers low-frequency color and illumination information as well as high-frequency structural details through band-specific objectives. Moreover, the distillation process of PSD is degradation-aware. We estimate degradation-aware weights through a physical head and combine them with ground-truth-guided reliability masks to selectively retain valuable teacher guidance. Experiments on the UIEB, LSUI, and EUVP datasets validate the effectiveness of the proposed method. Furthermore, we demonstrate the benefits of enhanced images for downstream perception tasks, including object detection. Deployment on a self-developed ROV further demonstrates its practical applicability in real-world underwater scenarios.