# Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt arXiv: https://arxiv.org/abs/2305.04430 ยท HTML: https://mlsanity.com/paper/2305.04430/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Builds on 33 of its 56 references that are in the map. - First posted on arXiv 8 May 2023. ## Builds on (most cited first, 30 of 33) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014) - [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021) - [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022) - [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022) - [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019) - [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021) - [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021) - [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023) - [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021) - [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018) - [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019) - [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017) - [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) - [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) - [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021) - [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) - [Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images](https://mlsanity.com/paper/1904.02904/) (2019) - [Gated Context Aggregation Network for Image Dehazing and Deraining](https://mlsanity.com/paper/1811.08747/) (2018) - [WaveFill: A Wavelet-based Generation Network for Image Inpainting](https://mlsanity.com/paper/2107.11027/) (2021) - [AWNet: Attentive Wavelet Network for Image ISP](https://mlsanity.com/paper/2008.09228/) (2020) - [DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing](https://mlsanity.com/paper/2104.08911/) (2021) - [NTIRE 2020 Challenge on NonHomogeneous Dehazing](https://mlsanity.com/paper/2005.03457/) (2020) - [Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution](https://mlsanity.com/paper/1809.04508/) (2018) - [A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning](https://mlsanity.com/paper/2104.08902/) (2021) ## Built on by (most cited first, 8 of 8) - [GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval](https://mlsanity.com/paper/2407.12431/) (2024) - [NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results](https://mlsanity.com/paper/2404.14248/) (2024) - [Towards Image Ambient Lighting Normalization](https://mlsanity.com/paper/2403.18730/) (2024) - [Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design](https://mlsanity.com/paper/2504.14075/) (2025) - [NTIRE 2025 Image Shadow Removal Challenge Report](https://mlsanity.com/paper/2506.15524/) (2025) - [NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results](https://mlsanity.com/paper/2510.13670/) (2025) - [UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization](https://mlsanity.com/paper/2604.13383/) (2026) - [Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling](https://mlsanity.com/paper/2606.25732/) (2026) ## Abstract (arXiv) Haze usually leads to deteriorated images with low contrast, color shift and structural distortion. We observe that many deep learning based models exhibit exceptional performance on removing homogeneous haze, but they usually fail to address the challenge of non-homogeneous dehazing. Two main factors account for this situation. Firstly, due to the intricate and non uniform distribution of dense haze, the recovery of structural and chromatic features with high fidelity is challenging, particularly in regions with heavy haze. Secondly, the existing small scale datasets for non-homogeneous dehazing are inadequate to support reliable learning of feature mappings between hazy images and their corresponding haze-free counterparts by convolutional neural network (CNN)-based models. To tackle these two challenges, we propose a novel two branch network that leverages 2D discrete wavelete transform (DWT), fast Fourier convolution (FFC) residual block and a pretrained ConvNeXt model. Specifically, in the DWT-FFC frequency branch, our model exploits DWT to capture more high-frequency features. Moreover, by taking advantage of the large receptive field provided by FFC residual blocks, our model is able to effectively explore global contextual information and produce images with better perceptual quality. In the prior knowledge branch, an ImageNet pretrained ConvNeXt as opposed to Res2Net is adopted. This enables our model to learn more supplementary information and acquire a stronger generalization ability. The feasibility and effectiveness of the proposed method is demonstrated via extensive experiments and ablation studies. The code is available at https://github.com/zhouh115/DWT-FFC.