# Curricular Contrastive Regularization for Physics-aware Single Image Dehazing

arXiv: https://arxiv.org/abs/2303.14218 · HTML: https://mlsanity.com/paper/2303.14218/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 22 of 22)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (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)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization](https://mlsanity.com/paper/1807.00230/) (2018)
- [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)
- [Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images](https://mlsanity.com/paper/1904.02904/) (2019)
- [Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding](https://mlsanity.com/paper/1808.01265/) (2018)
- [Gated Context Aggregation Network for Image Dehazing and Deraining](https://mlsanity.com/paper/1811.08747/) (2018)
- [From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data](https://mlsanity.com/paper/2108.02934/) (2021)
- [Curriculum DeepSDF](https://mlsanity.com/paper/2003.08593/) (2020)
- [HCSC: Hierarchical Contrastive Selective Coding](https://mlsanity.com/paper/2202.00455/) (2022)

## Built on by (most cited first, 30 of 83)

- [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024)
- [Restoring Images in Adverse Weather Conditions via Histogram Transformer](https://mlsanity.com/paper/2407.10172/) (2024)
- [Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration](https://mlsanity.com/paper/2408.15994/) (2024)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing](https://mlsanity.com/paper/2403.01105/) (2024)
- [Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network](https://mlsanity.com/paper/2406.07966/) (2024)
- [Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2403.01497/) (2024)
- [Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint](https://mlsanity.com/paper/2409.15739/) (2024)
- [Prompt-based Ingredient-Oriented All-in-One Image Restoration](https://mlsanity.com/paper/2309.03063/) (2023)
- [ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing](https://mlsanity.com/paper/2404.17825/) (2024)
- [Learning A Spiking Neural Network for Efficient Image Deraining](https://mlsanity.com/paper/2405.06277/) (2024)
- [SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing](https://mlsanity.com/paper/2304.08444/) (2023)
- [HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes](https://mlsanity.com/paper/2409.19833/) (2024)
- [Multi-task Image Restoration Guided By Robust DINO Features](https://mlsanity.com/paper/2312.01677/) (2023)
- [All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark](https://mlsanity.com/paper/2402.02090/) (2024)
- [Let Segment Anything Help Image Dehaze](https://mlsanity.com/paper/2306.15870/) (2023)
- [IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images](https://mlsanity.com/paper/2403.11870/) (2024)
- [Prompt-based test-time real image dehazing: a novel pipeline](https://mlsanity.com/paper/2309.17389/) (2023)
- [High-quality Image Dehazing with Diffusion Model](https://mlsanity.com/paper/2308.11949/) (2023)
- [Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration](https://mlsanity.com/paper/2309.06023/) (2023)
- [Adaptive Perception for Unified Visual Multi-modal Object Tracking](https://mlsanity.com/paper/2502.06583/) (2025)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [Self-Supervised Video Desmoking for Laparoscopic Surgery](https://mlsanity.com/paper/2403.11192/) (2024)
- [Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning](https://mlsanity.com/paper/2308.04142/) (2023)
- [When Schr"odinger Bridge Meets Real-World Image Dehazing with Unpaired Training](https://mlsanity.com/paper/2507.09524/) (2025)
- [Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing](https://mlsanity.com/paper/2509.20091/) (2025)
- [Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration](https://mlsanity.com/paper/2408.09241/) (2024)
- [DSwinIR: Rethinking Window-based Attention for Image Restoration](https://mlsanity.com/paper/2504.04869/) (2025)
- [Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images](https://mlsanity.com/paper/2504.09621/) (2025)
- [Learning Multi-scale Spatial-frequency Features for Image Denoising](https://mlsanity.com/paper/2506.16307/) (2025)

## Abstract (arXiv)

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are nonconsensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy image, and 2) corresponding restorations by other existing methods. Further, due to the different similarities between the embeddings of the clear image and negatives, the learning difficulty of the multiple components is intrinsically imbalanced. To tackle this issue, we customize a curriculum learning strategy to reweight the importance of different negatives. In addition, to improve the interpretability in the feature space, we build a physics-aware dual-branch unit according to the atmospheric scattering model. With the unit, as well as curricular contrastive regularization, we establish our dehazing network, named C2PNet. Extensive experiments demonstrate that our C2PNet significantly outperforms state-of-the-art methods, with extreme PSNR boosts of 3.94dB and 1.50dB, respectively, on SOTS-indoor and SOTS-outdoor datasets.