mlsanityData to 14 Oct 2026

WaterFlow: Heuristic Normalizing Flow for Underwater Image Enhancement and Beyond

arXiv 2308.00931 ↗First posted 2 Aug 2023cs.CVcited by 5

Not on the map. Why?

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.

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

35 of 60 references.

References · 35

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2017Mask R-CNNcited by 7,277
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  5. 2018YOLOv3: An Incremental Improvementcited by 2,659
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  8. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  9. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  10. 2017Focal Loss for Dense Object Detectioncited by 752
  11. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  12. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 349
23 more
  1. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 317
  2. 2019An Underwater Image Enhancement Benchmark Dataset and Beyondcited by 253
  3. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  4. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  5. 2021StyTr2: Image Style Transfer with Transformerscited by 187
  6. 2021Low-Light Image Enhancement with Normalizing Flowcited by 185
  7. 2019Fast Underwater Image Enhancement for Improved Visual Perceptioncited by 183
  8. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  9. 2021Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embeddingcited by 134
  10. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  11. 2018Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Datasetcited by 93
  12. 2023Implicit Neural Representation for Cooperative Low-light Image Enhancementcited by 92
  13. 2019Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutionscited by 90
  14. 2020Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolutioncited by 90
  15. 2023Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bankcited by 71
  16. 2022Pyramid Grafting Network for One-Stage High Resolution Saliency Detectioncited by 63
  17. 2022CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusioncited by 63
  18. 2022Implicit Motion Handling for Video Camouflaged Object Detectioncited by 60
  19. 2023A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusioncited by 47
  20. 2023Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyondcited by 26
  21. 2021Underwater Image Enhancement based on Deep Learning and Image Formation Modelcited by 16
  22. 2023Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registrationcited by 4
  23. 2023Contrastive Learning Based Recursive Dynamic Multi-Scale Network for Image Derainingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 0; 2026: 1.

5 papers.

  1. 2024A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learningcited by 9
  2. 2024HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learningcited by 7
  3. 2026Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Designcited by 5
  4. 2023CARNet: Collaborative Adversarial Resilience for Robust Underwater Image Enhancement and Perceptioncited by 0
  5. 2024Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Modelscited by 0