Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images, resulting in imperfect supervision. Such non-ideal supervision negatively affects the training process of learning-based de-weathering methods. In this work, we attempt to address the problem with a unified solution for various inconsistencies. Specifically, inspired by information bottleneck theory, we first develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image while removing most weather-related degradations. In particular, multiple adjacent frames of the current input are also fed into CLC to enhance the pseudo-label. Then we combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy (IAS). During testing, only the de-weathering model is used for inference. Experiments on two real-world de-weathering datasets show that our method helps existing de-weathering models achieve better performance. Codes are available at https://github.com/1180300419/imperfect-deweathering.

翻译：真实世界图像去天气化旨在移除各种不良天气相关伪影。由于无法同时捕捉图像对，现有的真实世界去天气化数据集在真实值图像与输入退化图像之间常存在光照、位置和纹理的不一致性，导致出现不完美监督。这种非理想监督对基于学习的去天气化方法的训练过程产生负面影响。在本文中，我们尝试通过一种统一的解决方案来应对多种不一致性问题。具体而言，受信息瓶颈理论启发，我们首先构建了一个一致性标签构建器（Consistent Label Constructor, CLC），用于生成与输入退化图像尽可能一致、同时去除大部分天气相关退化的伪标签。特别是，当前输入的多个相邻帧也被送入CLC以增强伪标签。随后，我们结合原始不完美标签和伪标签，通过所提出的信息分配策略（Information Allocation Strategy, IAS）联合监督去天气化模型。在测试阶段，仅使用去天气化模型进行推理。在两个真实世界去天气化数据集上的实验表明，我们的方法有助于现有去天气化模型获得更优性能。代码见 https://github.com/1180300419/imperfect-deweathering。