Nighttime image dehazing is a challenging task due to the presence of multiple types of adverse degrading effects including glow, haze, blurry, noise, color distortion, and so on. However, most previous studies mainly focus on daytime image dehazing or partial degradations presented in nighttime hazy scenes, which may lead to unsatisfactory restoration results. In this paper, we propose an end-to-end transformer-based framework for nighttime haze removal, called NightHazeFormer. Our proposed approach consists of two stages: supervised pre-training and semi-supervised fine-tuning. During the pre-training stage, we introduce two powerful priors into the transformer decoder to generate the non-learnable prior queries, which guide the model to extract specific degradations. For the fine-tuning, we combine the generated pseudo ground truths with input real-world nighttime hazy images as paired images and feed into the synthetic domain to fine-tune the pre-trained model. This semi-supervised fine-tuning paradigm helps improve the generalization to real domain. In addition, we also propose a large-scale synthetic dataset called UNREAL-NH, to simulate the real-world nighttime haze scenarios comprehensively. Extensive experiments on several synthetic and real-world datasets demonstrate the superiority of our NightHazeFormer over state-of-the-art nighttime haze removal methods in terms of both visually and quantitatively.

翻译：夜间图像去雾是一项具有挑战性的任务，原因在于图像中存在多种类型的有害退化效应，包括光晕、雾霾、模糊、噪声、色彩失真等。然而，以往的研究大多聚焦于白天图像去雾或夜间雾霾场景中的部分退化问题，这可能导致复原效果不佳。本文提出了一种基于Transformer的端到端夜间去雾框架，命名为NightHazeFormer。该方法包含两个阶段：有监督预训练和半监督微调。在预训练阶段，我们向Transformer解码器引入两种强先验信息，用于生成不可学习的先验查询，从而引导模型提取特定的退化特征。在微调阶段，我们将生成的伪真实图像与输入的真实世界夜间雾霾图像配对，构成成对图像，并将其输入合成域以微调预训练模型。这种半监督微调范式有助于提升模型在真实域中的泛化能力。此外，我们还提出了一个大规模合成数据集UNREAL-NH，用于全面模拟真实世界夜间雾霾场景。在多个合成与真实世界数据集上的广泛实验表明， NightHazeFormer在视觉效果和定量指标上均优于当前最先进的夜间去雾方法。