ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Farewell to CycleGAN: Single GAN with decoupled constraint for unpaired image dehazingNeurocomputing, 2025
- Restoring vision in hazy weather with hierarchical contrastive learningPattern Recognition, 2023
- Robust kernel principal component analysis with optimal meanNeural Networks, 2022
- Unpaired Image Dehazing With Physical-Guided Restoration and Depth-Guided RefinementIEEE Signal Processing Letters, 2022
- Second-order component analysis for fault detectionJournal of Process Control, 2021
- You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural NetworkInternational Journal of Computer Vision, 2021
- Dynamic neural orthogonal mapping for fault detectionInternational Journal of Machine Learning and Cybernetics, 2021
- DD-CycleGAN: Unpaired image dehazing via Double-Discriminator Cycle-Consistent Generative Adversarial NetworkEngineering Applications of Artificial Intelligence, 2019
- A Fast Single Image Haze Removal Algorithm Using Color Attenuation PriorIEEE Transactions on Image Processing, 2015
- Constrained Optimization and Lagrange Multiplier Methods1982