# ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing

arXiv: https://arxiv.org/abs/2404.17825 · HTML: https://mlsanity.com/paper/2404.17825/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 27 Apr 2024.

## Builds on (most cited first, 25 of 25)

- [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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (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)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Self-supervised Co-training for Video Representation Learning](https://mlsanity.com/paper/2010.09709/) (2020)
- [GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing](https://mlsanity.com/paper/1908.03245/) (2019)
- [Curricular Contrastive Regularization for Physics-aware Single Image Dehazing](https://mlsanity.com/paper/2303.14218/) (2023)
- [Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing](https://mlsanity.com/paper/1805.05308/) (2018)
- [Unpaired Deep Image Deraining Using Dual Contrastive Learning](https://mlsanity.com/paper/2109.02973/) (2021)
- [Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection](https://mlsanity.com/paper/2205.03346/) (2022)
- [You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network](https://mlsanity.com/paper/2006.16829/) (2020)
- [UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2205.01871/) (2022)
- [Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning](https://mlsanity.com/paper/2203.07677/) (2022)
- [Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning](https://mlsanity.com/paper/2212.11473/) (2022)
- [Estimating Fine-Grained Noise Model via Contrastive Learning](https://mlsanity.com/paper/2204.01716/) (2022)
- [Second-Order Component Analysis for Fault Detection](https://mlsanity.com/paper/2103.07303/) (2021)

## Built on by (most cited first, 16 of 16)

- [Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training](https://mlsanity.com/paper/2503.15017/) (2025)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video](https://mlsanity.com/paper/2412.11395/) (2024)
- [CoA: Towards Real Image Dehazing via Compression-and-Adaptation](https://mlsanity.com/paper/2504.05590/) (2025)
- [UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior](https://mlsanity.com/paper/2501.06818/) (2025)
- [DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model](https://mlsanity.com/paper/2504.17732/) (2025)
- [Hierarchical Semantic-Visual Fusion of Visible and Near-infrared Images for Long-range Haze Removal](https://mlsanity.com/paper/2507.03893/) (2025)
- [WeatherCycle: Unpaired Multi-Weather Restoration via Color Space Decoupled Cycle Learning](https://mlsanity.com/paper/2509.23150/) (2025)
- [U-Net-Like Spiking Neural Networks for Single Image Dehazing](https://mlsanity.com/paper/2512.23950/) (2025)
- [Towards Optimal Aggregation of Varying Range Dependencies in Haze Removal](https://mlsanity.com/paper/2408.12317/) (2024)
- [Luminance Component Analysis for Exposure Correction](https://mlsanity.com/paper/2411.16325/) (2024)
- [Learning Unpaired Image Dehazing with Physics-based Rehazy Generation](https://mlsanity.com/paper/2506.12824/) (2025)
- [Learning Implicit Neural Degradation Representation for Unpaired Image Dehazing](https://mlsanity.com/paper/2511.13110/) (2025)
- [Equivariant Learning for Unsupervised Image Dehazing](https://mlsanity.com/paper/2601.13986/) (2026)
- [Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion](https://mlsanity.com/paper/2603.21820/) (2026)
- [HazeSpikeMamba: Coupling Spiking-Inspired and State-Space Features for Self-Supervised Real-World Dehazing](https://mlsanity.com/paper/2608.06886/) (2026)

## Abstract (arXiv)

Unpaired image dehazing (UID) holds significant research importance due to the challenges in acquiring haze/clear image pairs with identical backgrounds. This paper proposes a novel method for UID named Orthogonal Decoupling Contrastive Regularization (ODCR). Our method is grounded in the assumption that an image consists of both haze-related features, which influence the degree of haze, and haze-unrelated features, such as texture and semantic information. ODCR aims to ensure that the haze-related features of the dehazing result closely resemble those of the clear image, while the haze-unrelated features align with the input hazy image. To accomplish the motivation, Orthogonal MLPs optimized geometrically on the Stiefel manifold are proposed, which can project image features into an orthogonal space, thereby reducing the relevance between different features. Furthermore, a task-driven Depth-wise Feature Classifier (DWFC) is proposed, which assigns weights to the orthogonal features based on the contribution of each channel's feature in predicting whether the feature source is hazy or clear in a self-supervised fashion. Finally, a Weighted PatchNCE (WPNCE) loss is introduced to achieve the pulling of haze-related features in the output image toward those of clear images, while bringing haze-unrelated features close to those of the hazy input. Extensive experiments demonstrate the superior performance of our ODCR method on UID.