Hybrid Adverse Conditions
HAC is a dataset for learning and benchmarking arbitrary Hybrid Adverse Conditions restoration. HAC contains 31 scenarios composed of an arbitrary combination of five common weather, with a total of 316K adverse-weather/clean pairs.
Source: Restoring Images Captured in Arbitrary Hybrid Adverse Weather Conditions in One Go
Image Source: Restoring Images Captured in Arbitrary Hybrid Adverse Weather Conditions in One Go