Recently, numerous sand dust removal algorithms have been proposed. To our best knowledge, however, most methods evaluated their performance in a no-reference way using few selected real-world images from the internet. It is unclear how to quantitatively analyze the performance of the algorithms in a supervised way. Moreover, due to the absence of large-scale datasets, there are no well-known sand dust reconstruction report algorithms up till now. To bridge the gaps, we presented a comprehensive perceptual study and analysis of real-world sandstorm images, then constructed a Sand-dust Image Reconstruction Benchmark(SIRB) for training Convolutional Neural Networks(CNNs) and evaluating the algorithm's performance. We adopted the existing image transformation neural network trained on SIRB as the baseline to illustrate the generalization of SIRB for training CNNs. Finally, we conducted a comprehensive evaluation to demonstrate the performance and limitations of the sandstorm enhancement algorithms, which shed light on future research in sandstorm image reconstruction.
展开▼
