FreePath：用神经平均自由程框架做图像去雾
FreePath: Neural Mean Free Path for Image Dehazing
一篇去雾新论文，思路挺特别：不估大气参数，改学光在雾里能传多远，在 CDD-11 和 RTTS 上效果都更好。
论文提出 FreePath，把图像去雾建模为特征空间中的路径状态恢复，而不是估计大气散射参数。模型在残差编码器-解码器内通过 Mean Free Path Residual Block 学习路径场和碰撞场，并用 FreePath State Conservation Integration 在深层特征聚合时保持已恢复的路径状态。在 CDD-11 配对去雾数据集和真实 RTTS 场景上，FreePath 在全参考保真度和无参考感知质量上均超过代表性去雾基线方法。
FreePath: Neural Mean Free Path for Image Dehazing
Single image dehazing requires recovering scene radiance from visual responses that are weakened and veiled by participating media. Existing methods either invert explicit scattering variables, which can be unstable under complex scenes, or learn direct restoration mappings, which often discard the physical organization of haze formation. We present \emph{FreePath}, a neural mean free path framework for image dehazing. Instead of estimating atmospheric parameters, FreePath represents dehazing as feature space path state restoration, inspired by the expected distance a visual response can propagate before interacting with haze. Within a residual encoder and decoder, the Mean Free Path Residual Block learns path and collision fields to guide haze constrained correction, while FreePath State Conservation Integration preserves restored path states during deep feature aggregation. Experiments on paired CDD-11 haze images and real RTTS scenes show that FreePath consistently improves full reference fidelity, no reference perceptual quality, and visual faithfulness over representative dehazing baselines.