# Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement

arXiv: https://arxiv.org/abs/2308.11932 · HTML: https://mlsanity.com/paper/2308.11932/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 40 references that are in the map.
- First posted on arXiv 23 Aug 2023.

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

- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [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)
- [Underwater Ranker: Learn Which Is Better and How to Be Better](https://mlsanity.com/paper/2208.06857/) (2022)
- [Uncertainty Inspired Underwater Image Enhancement](https://mlsanity.com/paper/2207.09689/) (2022)
- [UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space](https://mlsanity.com/paper/2103.07138/) (2021)

## Built on by (most cited first, 10 of 10)

- [HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning](https://mlsanity.com/paper/2411.18296/) (2024)
- [CoA: Towards Real Image Dehazing via Compression-and-Adaptation](https://mlsanity.com/paper/2504.05590/) (2025)
- [NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding](https://mlsanity.com/paper/2510.27481/) (2025)
- [UVLM: Benchmarking Video Language Model for Underwater World Understanding](https://mlsanity.com/paper/2507.02373/) (2025)
- [WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement](https://mlsanity.com/paper/2511.16321/) (2025)
- [Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement](https://mlsanity.com/paper/2508.04123/) (2025)
- [Enhancing Underwater Images via Adaptive Semantic-aware Codebook Learning](https://mlsanity.com/paper/2602.10586/) (2026)
- [Advancing Visual Reliability: Color-Accurate Underwater Image Enhancement for Real-Time Underwater Missions](https://mlsanity.com/paper/2603.16363/) (2026)
- [UniV2D: Bridging Visual Restoration and Semantic Perception for Underwater Salient Object Detection](https://mlsanity.com/paper/2605.07146/) (2026)
- [DY-LUT: Depth-Aware YCbCr Lookup Tables for Real-Time Underwater Image Enhancement](https://mlsanity.com/paper/2607.22801/) (2026)

## Abstract (arXiv)

Visually restoring underwater scenes primarily involves mitigating interference from underwater media. Existing methods ignore the inherent scale-related characteristics in underwater scenes. Therefore, we present the synergistic multi-scale detail refinement via intrinsic supervision (SMDR-IS) for enhancing underwater scene details, which contain multi-stages. The low-degradation stage from the original images furnishes the original stage with multi-scale details, achieved through feature propagation using the Adaptive Selective Intrinsic Supervised Feature (ASISF) module. By using intrinsic supervision, the ASISF module can precisely control and guide feature transmission across multi-degradation stages, enhancing multi-scale detail refinement and minimizing the interference from irrelevant information in the low-degradation stage. In multi-degradation encoder-decoder framework of SMDR-IS, we introduce the Bifocal Intrinsic-Context Attention Module (BICA). Based on the intrinsic supervision principles, BICA efficiently exploits multi-scale scene information in images. BICA directs higher-resolution spaces by tapping into the insights of lower-resolution ones, underscoring the pivotal role of spatial contextual relationships in underwater image restoration. Throughout training, the inclusion of a multi-degradation loss function can enhance the network, allowing it to adeptly extract information across diverse scales. When benchmarked against state-of-the-art methods, SMDR-IS consistently showcases superior performance. The code is publicly available at: https://github.com/zhoujingchun03/SMDR-IS.