Existing methods attempt to improve models' generalization ability on real-world hazy images by exploring well-designed training schemes (e.g., CycleGAN, prior loss). However, most of them need very complicated training procedures to achieve satisfactory results. In this work, we present a totally novel testing pipeline called Prompt-based Test-Time Dehazing (PTTD) to help generate visually pleasing results of real-captured hazy images during the inference phase. We experimentally find that given a dehazing model trained on synthetic data, by fine-tuning the statistics (i.e., mean and standard deviation) of encoding features, PTTD is able to narrow the domain gap, boosting the performance of real image dehazing. Accordingly, we first apply a prompt generation module (PGM) to generate a visual prompt, which is the source of appropriate statistical perturbations for mean and standard deviation. And then, we employ the feature adaptation module (FAM) into the existing dehazing models for adjusting the original statistics with the guidance of the generated prompt. Note that, PTTD is model-agnostic and can be equipped with various state-of-the-art dehazing models trained on synthetic hazy-clean pairs. Extensive experimental results demonstrate that our PTTD is flexible meanwhile achieves superior performance against state-of-the-art dehazing methods in real-world scenarios. The source code of our PTTD will be made available at https://github.com/cecret3350/PTTD-Dehazing.

翻译：现有方法试图通过探索精心设计的训练方案（如CycleGAN、先验损失）来提升模型在真实雾霾图像上的泛化能力。然而，大多数方法需要极其复杂的训练流程才能取得满意结果。本文提出一种全新的测试流水线——基于提示的测试时去雾（Prompt-based Test-Time Dehazing, PTTD），旨在推理阶段帮助生成视觉上令人满意的真实拍摄雾霾图像。实验发现，给定一个在合成数据上训练的去雾模型，通过微调编码特征的统计量（即均值和标准差），PTTD能够缩小域差距，提升真实图像去雾的性能。据此，我们首先应用提示生成模块（Prompt Generation Module, PGM）生成视觉提示，该提示是为均值和标准差提供适当统计扰动的来源。随后，我们采用特征适应模块（Feature Adaptation Module, FAM）嵌入现有去雾模型中，在生成提示的引导下调整原始统计量。值得注意的是，PTTD是模型无关的，可适配多种在合成雾霾-清晰图像对训练的最先进去雾模型。大量实验结果表明，我们的PTTD灵活且在实际场景中相比最先进去雾方法实现了更优异的性能。PTTD的源代码将在https://github.com/cecret3350/PTTD-Dehazing提供。