Li Boyi, Ren Wenqi, Fu Dengpan, Tao Dacheng, Feng Dan, Zeng Wenjun, Wang Zhangyang
IEEE Trans Image Process. 2018 Aug 30. doi: 10.1109/TIP.2018.2867951.
In this paper, we present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of stateof- the-art dehazing algorithms, and suggest promising future directions.
在本文中，我们使用一个新的大规模基准数据集，即逼真单图像去雾（RESIDE），对现有的单图像去雾算法进行了全面的研究和评估。该数据集包含合成和真实世界的模糊图像，突出了不同的数据来源和图像内容，并分为五个子集，每个子集用于不同的训练或评估目的。我们还提供了丰富多样的去雾算法评估标准，从全参考指标到无参考指标，再到主观评估和新颖的任务驱动评估。在RESIDE上进行的实验揭示了当前最先进的去雾算法的比较结果和局限性，并提出了有前景的未来发展方向。
