Image Dehazing

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

15 leaderboard tables shown for this task, 15 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 15 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

17 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 157 papers with code (295 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Contrastive Learning for Compact Single Image Dehazing
  19 Apr 2021 10 repositories listed
  In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
• GMAN: A Graph Multi-Attention Network for Traffic Prediction
  11 Nov 2019 6 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  Between the encoder and the decoder, a transform attention layer is applied to convert the encoded traffic features to generate the sequence representations of future time steps as the input of the decoder.
• FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
  18 Nov 2019 4 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  The FFA-Net architecture consists of three key components: 1) A novel Feature Attention (FA) module combines Channel Attention with Pixel Attention mechanism, considering that different channel-wise features contain…
• MAXIM: Multi-Axis MLP for Image Processing
  9 Jan 2022 3 repositories listed Syntology ran 27 of 46 samples · 19 unverified
  In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks.
• Improving Image Restoration by Revisiting Global Information Aggregation
  8 Dec 2021 3 repositories listed
  Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images.
• Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images
  5 Apr 2019 3 repositories listed
  Characterized by dense and homogeneous hazy scenes, Dense-Haze contains 33 pairs of real hazy and corresponding haze-free images of various outdoor scenes.
• Generic Model-Agnostic Convolutional Neural Network for Single Image Dehazing
  5 Oct 2018 3 repositories listed
  Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis.
• Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing
  14 May 2018 3 repositories listed
  In this paper, we present an end-to-end network, called Cycle-Dehaze, for single image dehazing problem, which does not require pairs of hazy and corresponding ground truth images for training.
• DehazeNet: An End-to-End System for Single Image Haze Removal
  28 Jan 2016 3 repositories listed
  The key to achieve haze removal is to estimate a medium transmission map for an input hazy image.
• MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration
  8 Jan 2025 2 repositories listed
  This variant leverages the Taylor expansion to approximate the Softmax-attention and utilizes the concept of norm-preserving mapping to approximate the remainder of the first-order Taylor expansion, resulting in a…
• Deep Variational Bayesian Modeling of Haze Degradation Process
  4 Dec 2024 2 repositories listed Syntology ran 4 of 14 samples · 10 unverified
  To account for such uncertainties and factors involved in haze degradation, we introduce a variational Bayesian framework for single image dehazing.
• Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
  12 Sep 2023 2 repositories listed
  Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks.
• Frequency Compensated Diffusion Model for Real-scene Dehazing
  21 Aug 2023 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze.
• Image Dehazing Transformer With Transmission-Aware 3D Position Embedding
  1 Jan 2022 2 repositories listed
  Though Transformer has occupied various computer vision tasks, directly leveraging Transformer for image dehazing is challenging: 1) it tends to result in ambiguous and coarse details that are undesired for image…
• Blind Video Temporal Consistency via Deep Video Prior
  22 Oct 2020 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Extensive quantitative and perceptual experiments show that our approach obtains superior performance than state-of-the-art methods on blind video temporal consistency.
• Distilling Image Dehazing With Heterogeneous Task Imitation
  1 Jun 2020 2 repositories listed
  The student network imitates the task of image reconstruction in the teacher network.
• Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
  12 May 2020 2 repositories listed Syntology ran 2 of 6 samples · 4 unverified
  Recently, CNN based end-to-end deep learning methods achieve superiority in Image Dehazing but they tend to fail drastically in Non-homogeneous dehazing.
• Lower Bound on Transmission Using Non-Linear Bounding Function in Single Image Dehazing
  28 Feb 2020 2 repositories listed
  The accuracy and effectiveness of SID depends on accurate value of transmission and atmospheric light.
• Single Image Haze Removal using a Generative Adversarial Network
  22 Oct 2018 2 repositories listed
  Traditional methods to remove haze from images rely on estimating a transmission map.
• I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images
  13 Apr 2018 2 repositories listed
  This represents an important advantage of the I-HAZE dataset that allows us to objectively compare the existing image dehazing techniques using traditional image quality metrics such as PSNR and SSIM.
• An All-in-One Network for Dehazing and Beyond
  20 Jul 2017 2 repositories listed
  This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net).
• Forward-only Diffusion Probabilistic Models
  22 May 2025 1 repository listed
  This work presents a forward-only diffusion (FoD) approach for generative modelling.
• Degradation-Aware Feature Perturbation for All-in-One Image Restoration
  19 May 2025 1 repository listed Syntology ran 6 of 7 samples · 1 unverified · 7 pointer-only (licence)
  To address this issue, motivated by the routing strategy, we propose DFPIR, a novel all-in-one image restorer that introduces Degradation-aware Feature Perturbations(DFP) to adjust the feature space to align with the…
• A Preliminary Study for GPT-4o on Image Restoration
  8 May 2025 1 repository listed
  OpenAI's GPT-4o model, integrating multi-modal inputs and outputs within an autoregressive architecture, has demonstrated unprecedented performance in image generation.
• WDMamba: When Wavelet Degradation Prior Meets Vision Mamba for Image Dehazing
  7 May 2025 1 repository listed
  In this paper, we reveal a novel haze-specific wavelet degradation prior observed through wavelet transform analysis, which shows that haze-related information predominantly resides in low-frequency components.
• Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing
  24 Apr 2025 1 repository listed
  Single-image dehazing is an important topic in remote sensing applications, enhancing the quality of acquired images and increasing object detection precision.
• SAD-Net: a full spectral self-attention detail enhancement network for single image dehazing
  7 Apr 2025 1 repository listed
  However, existing dehazing methods using vanilla convolution only extract features in the temporal domain and lack the ability to capture multi-directional information.
• Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing
  25 Mar 2025 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  Existing real-world image dehazing methods primarily attempt to fine-tune pre-trained models or adapt their inference procedures, thus heavily relying on the pre-trained models and associated training data.
• Real-World Remote Sensing Image Dehazing: Benchmark and Baseline
  23 Mar 2025 1 repository listed
  To address this, we introduce Real-World Remote Sensing Hazy Image Dataset (RRSHID), the first large-scale dataset featuring real-world hazy and dehazed image pairs across diverse atmospheric conditions.
• ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing
  21 Mar 2025 1 repository listed
  Recent approaches using large-scale pretrained diffusion models for image dehazing improve perceptual quality but often suffer from hallucination issues, producing unfaithful dehazed image to the original one.

Syntology lines on 9 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.