# GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing

arXiv: https://arxiv.org/abs/2103.13998 · HTML: https://mlsanity.com/paper/2103.13998/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 87 references that are in the map.
- First posted on arXiv 25 Mar 2021.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [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)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Essentially No Barriers in Neural Network Energy Landscape](https://mlsanity.com/paper/1803.00885/) (2018)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [FFA-Net: Feature Fusion Attention Network for Single Image Dehazing](https://mlsanity.com/paper/1911.07559/) (2019)
- [The Loss Surfaces of Multilayer Networks](https://mlsanity.com/paper/1412.0233/) (2014)
- [Multi-Scale Boosted Dehazing Network with Dense Feature Fusion](https://mlsanity.com/paper/2004.13388/) (2020)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Distilling Object Detectors with Fine-grained Feature Imitation](https://mlsanity.com/paper/1906.03609/) (2019)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Burst Denoising with Kernel Prediction Networks](https://mlsanity.com/paper/1712.02327/) (2017)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Gated Fusion Network for Single Image Dehazing](https://mlsanity.com/paper/1804.00213/) (2018)

## Built on by (most cited first, 14 of 14)

- [GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval](https://mlsanity.com/paper/2407.12431/) (2024)
- [Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing](https://mlsanity.com/paper/2503.19262/) (2025)
- [ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer](https://mlsanity.com/paper/2406.02559/) (2024)
- [AttentionLut: Attention Fusion-based Canonical Polyadic LUT for Real-time Image Enhancement](https://mlsanity.com/paper/2401.01569/) (2024)
- [DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer](https://mlsanity.com/paper/2407.05169/) (2024)
- [Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt](https://mlsanity.com/paper/2305.04430/) (2023)
- [RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing Image Dehazing](https://mlsanity.com/paper/2405.09083/) (2024)
- [HazeCLIP: Towards Language Guided Real-World Image Dehazing](https://mlsanity.com/paper/2407.13719/) (2024)
- [Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation](https://mlsanity.com/paper/2403.06452/) (2024)
- [A2-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks](https://mlsanity.com/paper/2603.10685/) (2026)
- [YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions](https://mlsanity.com/paper/2410.17734/) (2024)
- [FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal](https://mlsanity.com/paper/2603.19036/) (2026)
- [Multi-Knowledge-oriented Nighttime Haze Imaging Enhancer for Vision-driven Intelligent Systems](https://mlsanity.com/paper/2502.07351/) (2025)
- [UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization](https://mlsanity.com/paper/2604.13383/) (2026)

## Abstract (arXiv)

We propose an enhanced multi-scale network, dubbed GridDehazeNet+, for single image dehazing. The proposed dehazing method does not rely on the Atmosphere Scattering Model (ASM), and an explanation as to why it is not necessarily performing the dimension reduction offered by this model is provided. GridDehazeNet+ consists of three modules: pre-processing, backbone, and post-processing. The trainable pre-processing module can generate learned inputs with better diversity and more pertinent features as compared to those derived inputs produced by hand-selected pre-processing methods. The backbone module implements multi-scale estimation with two major enhancements: 1) a novel grid structure that effectively alleviates the bottleneck issue via dense connections across different scales; 2) a spatial-channel attention block that can facilitate adaptive fusion by consolidating dehazing-relevant features. The post-processing module helps to reduce the artifacts in the final output. Due to domain shift, the model trained on synthetic data may not generalize well on real data. To address this issue, we shape the distribution of synthetic data to match that of real data, and use the resulting translated data to finetune our network. We also propose a novel intra-task knowledge transfer mechanism that can memorize and take advantage of synthetic domain knowledge to assist the learning process on the translated data. Experimental results demonstrate that the proposed method outperforms the state-of-the-art on several synthetic dehazing datasets, and achieves the superior performance on real-world hazy images after finetuning.