From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data

Understand

Single image dehazing is a challenging task, for which the domain shift between synthetic training data and real-world testing images usually leads to degradation of existing methods.

• To address this issue, we propose a novel image dehazing framework collaborating with unlabeled real data.
• First, we develop a disentangled image dehazing network (DID-Net), which disentangles the feature representations into three component maps, i.e.
• the latent haze-free image, the transmission map, and the global atmospheric light estimate, respecting the physical model of a haze process.