Two-step image dehazing with intra-domain and inter-domain adaptation

Intra-domain and inter-domain gaps are widely presented in image processing tasks due to data distribution differences. In the field of dehazing, particular previous works have paid attention gap between synthetic domain real domain. However, those methods only establish connection from without considering significant shift within (intra-domain gap). this work, we propose a Two-Step Dehazing Network (TSDN) with an intra-domain adaptation constrained adaptation. First, subdivide distributions into subsets mine optimal subset (easy samples) by loss-based supervision. To alleviate domain, align other adversarial learning. Finally, conduct alleviating domains as well Extensive experimental results demonstrate that our framework performs favorably against state-of-the-art algorithms both on datasets datasets.