Learning to Restore Arbitrary Hybrid adverse weather Conditions in one go

Abstract

Adverse conditions typically suffer from stochastic hybrid weather degradations (e.g., rainy and hazy night), while existing image restoration algorithms envisage that weather degradations occur independently, thus may fail to handle real-world complicated scenarios. Besides, supervised training is not feasible due to the lack of comprehensive paired dataset to characterize hybrid weather conditions. To this end, we have advanced the forementioned limitations with two tactics: framework and data. First, we present a novel unified framework, dubbed RAHC, to Restore Arbitrary Hybrid adverse weather Conditions in one go. Specifically, our RAHC leverages a multi-head aggregation architecture to learn multiple degradation representation subspaces and then constrains the network to flexibly handle multiple hybrid adverse weather in a unified paradigm through a discrimination mechanism in the output space. Furthermore, we devise a reconstruction vectors aided scheme to provide auxiliary visual content cues for reconstruction, thus can comfortably cope with hybrid scenarios with insufficient remaining image constituents. Second, we establish a new dataset, termed HAC, for learning and benchmarking arbitrary Hybrid Adverse Conditions restoration. HAC contains 31 scenarios composed of an arbitrary fusion of five common weather, with a total of $\sim 316K$ adverse-weather/clean pairs. As for fabrication, the training set is automatically generated by a dedicated AdverseGAN with no-frills labor, while the test set is manually modulated by experts for authoritative evaluation. Extensive experiments yield superior results and in particular establish new state-of-the-art results on both HAC and conventional datasets.