# WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond

arXiv: https://arxiv.org/abs/2308.00931 · HTML: https://mlsanity.com/paper/2308.00931/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 30 of 35)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset](https://mlsanity.com/paper/1811.01343/) (2018)
- [Implicit Neural Representation for Cooperative Low-light Image Enhancement](https://mlsanity.com/paper/2303.11722/) (2023)
- [Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions](https://mlsanity.com/paper/1901.05320/) (2019)
- [Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution](https://mlsanity.com/paper/2003.07018/) (2020)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion](https://mlsanity.com/paper/2211.10960/) (2022)
- [Implicit Motion Handling for Video Camouflaged Object Detection](https://mlsanity.com/paper/2203.07363/) (2022)

## Built on by (most cited first, 5 of 5)

- [A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning](https://mlsanity.com/paper/2405.19684/) (2024)
- [HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning](https://mlsanity.com/paper/2411.18296/) (2024)
- [Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design](https://mlsanity.com/paper/2603.01767/) (2026)
- [CARNet: Collaborative Adversarial Resilience for Robust Underwater Image Enhancement and Perception](https://mlsanity.com/paper/2309.01102/) (2023)
- [Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models](https://mlsanity.com/paper/2409.06420/) (2024)

## Abstract (arXiv)

Underwater images suffer from light refraction and absorption, which impairs visibility and interferes the subsequent applications. Existing underwater image enhancement methods mainly focus on image quality improvement, ignoring the effect on practice. To balance the visual quality and application, we propose a heuristic normalizing flow for detection-driven underwater image enhancement, dubbed WaterFlow. Specifically, we first develop an invertible mapping to achieve the translation between the degraded image and its clear counterpart. Considering the differentiability and interpretability, we incorporate the heuristic prior into the data-driven mapping procedure, where the ambient light and medium transmission coefficient benefit credible generation. Furthermore, we introduce a detection perception module to transmit the implicit semantic guidance into the enhancement procedure, where the enhanced images hold more detection-favorable features and are able to promote the detection performance. Extensive experiments prove the superiority of our WaterFlow, against state-of-the-art methods quantitatively and qualitatively.