基于跨域流形共识的解耦式图像去雾
Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus
提出跨域不变流形（CIM）对齐多域特征，并用共识密度驱动的对比学习优化，可复用于其他跨域底层视觉任务（如去雨、去噪）以消除域偏差；物理引导的HSV分解网络为颜色保真提供了解耦思路。
原文依据 we propose a unified framework centered on a Cross-domain Invariant Manifold (CIM), which aligns multi-domain features into a unified latent space through shared scattering semantics.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前去雾方法面临两个相互交织的挑战：（1）由于单域和经验整合的多域方法中域特定干扰导致的雾相关特征误识别，以及（2）雾引起的颜色纠缠导致的严重色度失真。为克服这些局限，我们提出了一个以跨域不变流形（CIM）为中心的统一框架，通过共享散射语义将多域特征对齐到统一的潜空间。该流形通过共识密度驱动的对比学习进行优化，有效增强跨域一致性同时消除域特定偏差。在此结构化基础上，我们进一步引入解耦式架构，即物理引导的HSV分解网络，显式分离纠缠的颜色分量以确保稳健的颜色保真度。综合实验表明，我们的CIM-D框架达到了最优性能，有效消除了雾引起的颜色偏移并恢复了自然场景外观。
英文原文摘要 1104 字符
Current dehazing methods face two intertwined challenges: (1) the misidentification of haze-related features due to domain-specific interference in both single-domain and empirically integrated multi-domain approaches, and (2) severe chromatic distortion caused by haze-induced color entanglement. To overcome these limitations, we propose a unified framework centered on a Cross-domain Invariant Manifold (CIM), which aligns multi-domain features into a unified latent space through shared scattering semantics. The manifold is optimized via consensus-density-driven contrastive learning, effectively enhancing cross-domain consistency while eliminating domain-specific biases. Building upon this structured foundation, we further introduce a disentanglement-wise architecture, i.e., Physics-Guided HSV Decomposition Network, that explicitly separates entangled color components to ensure robust color fidelity. Comprehensive experiments demonstrate that our CIM-D framework achieves state-of-the-art performance, effectively eliminating haze-induced color shifts and restoring natural scene appearance.