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.
Abstract (translated)
未配对图像去雾(UID)具有重要研究价值,因为获取具有相同背景的雾/清晰图像对具有挑战性。本文提出了一种名为Orthogonal Decoupling Contrastive Regularization(ODCR)的新方法来解决UID。我们的方法基于一个假设,即图像由雾相关特征和雾无关特征(如纹理和语义信息)组成。ODCR旨在确保去雾结果的雾相关特征与清晰图像的雾相关特征相似,而雾无关特征与输入雾图像对齐。为了实现这一目标,我们提出了Orthogonal MLPs优化几何地在Stiefel维度的方法,这些方法可以投影图像特征到正交空间,从而降低不同特征之间的相关性。此外,我们还提出了一个基于任务的有条件深度卷积特征分类器(DWFC),其中基于每个通道特征对预测功能源是否为雾或清晰进行自监督的贡献为权重分配给正交特征。最后,我们引入了加权PatchNCE(WPNCE)损失,以实现将输出图像中雾相关特征向清晰图像的雾相关特征的拉动,同时将雾无关特征带到雾输入的附近。大量实验证明,我们的ODCR方法在UID上具有卓越的性能。
URL
https://arxiv.org/abs/2404.17825