NightHazeFormer：使用先验查询Transformer的单幅夜间雾霭去除
NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer
AI总结：
针对夜间复杂退化导致的去雾难题，提出两阶段NightHazeFormer，利用先验查询和半监督微调提升真实场景泛化，并构建UNREAL-NH数据集，效果优于现有方法。
摘要：
夜间图像去雾是一项具有挑战性的任务，因为图像中存在多种不利的退化效应，包括辉光、雾霭、模糊、噪声、颜色失真等。然而，以往大多数研究主要集中于白天图像去雾，或仅关注夜间雾天场景中呈现的部分退化，这可能导致不尽如人意的恢复结果。本文提出一种基于Transformer的端到端夜间去雾框架，称为NightHazeFormer。我们提出的方法包括两个阶段：有监督预训练和半监督微调。在预训练阶段，我们将两个强大的先验引入Transformer解码器，以生成不可学习的先验查询，引导模型提取特定退化。在微调阶段，我们将生成的伪真值与输入的真实世界夜间雾天图像组合为配对图像，并送入合成域，对预训练模型进行微调。这种半监督微调范式有助于提升模型向真实域的泛化能力。此外，我们还提出一个名为UNREAL-NH的大规模合成数据集，用于全面模拟真实世界的夜间雾天场景。在若干合成数据集和真实世界数据集上进行的大量实验表明，我们的NightHazeFormer在视觉效果和定量指标方面均优于最先进的夜间去雾方法。
英文摘要：
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.
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。
