# Self-Supervised Enhancement of Forward-Looking Sonar Images: Bridging Cross-Modal Degradation Gaps through Feature Space Transformation and Multi-Frame Fusion

arXiv: https://arxiv.org/abs/2504.10974 · HTML: https://mlsanity.com/paper/2504.10974/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 52 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Builds on (most cited first, 8 of 8)

- [XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?](https://mlsanity.com/paper/2503.23771/) (2025)
- [SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer](https://mlsanity.com/paper/2403.17004/) (2024)
- [SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection](https://mlsanity.com/paper/2403.06534/) (2024)
- [HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery](https://mlsanity.com/paper/2002.06460/) (2020)
- [RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing](https://mlsanity.com/paper/2503.10392/) (2025)
- [Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification](https://mlsanity.com/paper/2403.08271/) (2024)
- [Image-to-Height Domain Translation for Synthetic Aperture Sonar](https://mlsanity.com/paper/2112.06307/) (2021)
- [Self-Supervised Dual Contouring](https://mlsanity.com/paper/2405.18131/) (2024)

## Built on by (most cited first, 1 of 1)

- [BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations](https://mlsanity.com/paper/2608.23215/) (2026)

## Abstract (arXiv)

Enhancing forward-looking sonar images is critical for accurate underwater target detection. Current deep learning methods mainly rely on supervised training with simulated data, but the difficulty in obtaining high-quality real-world paired data limits their practical use and generalization. Although self-supervised approaches from remote sensing partially alleviate data shortages, they neglect the cross-modal degradation gap between sonar and remote sensing images. Directly transferring pretrained weights often leads to overly smooth sonar images, detail loss, and insufficient brightness. To address this, we propose a feature-space transformation that maps sonar images from the pixel domain to a robust feature domain, effectively bridging the degradation gap. Additionally, our self-supervised multi-frame fusion strategy leverages complementary inter-frame information to naturally remove speckle noise and enhance target-region brightness. Experiments on three self-collected real-world forward-looking sonar datasets show that our method significantly outperforms existing approaches, effectively suppressing noise, preserving detailed edges, and substantially improving brightness, demonstrating strong potential for underwater target detection applications.