mlsanityData to 7 Oct 2026

Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing

arXiv 2503.01136 ↗First posted 3 Mar 2025cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive results in diverse dehazing tasks, their quadratic complexity and lack of dehazing priors pose significant drawbacks for real-world applications. In this paper, guided by triple priors, Bright Channel Prior (BCP), Dark Channel Prior (DCP), and Histogram Equalization (HE), we propose a textitPrior-textitguided Hierarchical textitHarmonization Network (PGH2Net) for image dehazing. PGH2Net is built upon the UNet-like architecture with an efficient encoder and decoder, consisting of two module types: (1) Prior aggregation module that injects B/DCP and selects diverse contexts with gating attention. (2) Feature harmonization modules that subtract low-frequency components from spatial and channel aspects and learn more informative feature distributions to equalize the feature maps.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 26 of its 55 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

26 of 55 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  6. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  7. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  8. 2020Pre-Trained Image Processing Transformercited by 891
  9. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  10. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  11. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  12. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
14 more
  1. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  2. 2020Multi-Scale Boosted Dehazing Network with Dense Feature Fusioncited by 229
  3. 2019GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazingcited by 227
  4. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  5. 2019Orthogonal Convolutional Neural Networkscited by 122
  6. 2022HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutionscited by 103
  7. 2018O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor imagescited by 95
  8. 2023DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attentioncited by 90
  9. 2021Iterative Filter Adaptive Network for Single Image Defocus Deblurringcited by 85
  10. 2022MogaNet: Multi-order Gated Aggregation Networkcited by 59
  11. 2023Neural Degradation Representation Learning for All-In-One Image Restorationcited by 46
  12. 2021SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurringcited by 26
  13. 2023Mutual Information-driven Triple Interaction Network for Efficient Image Dehazingcited by 18
  14. 2023Mutual-Guided Dynamic Network for Image Fusioncited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 7.

12 papers.

  1. 2026UDPNet: Unleashing Depth-based Priors for Robust Image Dehazingcited by 3
  2. 2025Efficient Dual-domain Image Dehazing with Haze Prior Perceptioncited by 2
  3. 2025Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazingcited by 1
  4. 2026Learning Adaptive Dynamical Features via Multi-τ Liquid-Mamba for All-in-one Image Restorationcited by 1
  5. 2025Learning Unpaired Image Dehazing with Physics-based Rehazy Generationcited by 0
  6. 2025Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptationcited by 0
  7. 2025Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolutioncited by 0
  8. 2026From Physical Degradation Models to Task-Aware All-in-One Image Restorationcited by 0
  9. 2026QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibrationcited by 0
  10. 2026Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agentscited by 0
  11. 2026Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Modelscited by 0
  12. 2026GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restorationcited by 0