ODCR：用于非配对图像去雾的正交解耦对比正则化
ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing
AI总结：
针对非配对图像去雾问题，提出正交解耦对比正则化（ODCR）方法，通过在Stiefel流形上优化的正交MLP将图像特征投影到正交空间，解耦雾相关与雾无关特征，并利用深度特征分类器和加权PatchNCE损失实现特征对齐，显著提升去雾性能。
摘要：
由于获取背景相同的雾天/清晰图像对存在挑战，非配对图像去雾（UID）具有重要的研究意义。本文提出了一种名为正交解耦对比正则化（ODCR）的新型UID方法。该方法基于以下假设：图像既包含影响雾浓度的雾相关特征，也包含纹理和语义信息等雾无关特征。ODCR旨在确保去雾结果的雾相关特征与清晰图像紧密相似，而雾无关特征与输入雾天图像对齐。为实现这一目标，提出了在Stiefel流形上进行几何优化的正交MLP，能将图像特征投影到正交空间中，从而降低不同特征之间的相关性。此外，提出了一种任务驱动的深度特征分类器（DWFC），它以自监督方式根据每个通道特征在预测特征源是雾天还是清晰中的贡献，为正交特征分配权重。最后，引入了加权PatchNCE（WPNCE）损失，以将输出图像中的雾相关特征拉向清晰图像的特征，同时使雾无关特征接近雾天输入的特征。大量实验表明，ODCR方法在UID上具有优越的性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
