A Synthetic-to-Real Dehazing Method based on Domain Unification
This addresses the problem of domain shift in image dehazing for computer vision applications, but it appears incremental as it builds on existing synthetic-to-real approaches.
The paper tackles the performance drop in deep learning-based image dehazing when applied to real-world images due to distribution shift from imperfect clean data collection, proposing a synthetic-to-real method based on domain unification that significantly outperforms state-of-the-art methods on real-world images.
Due to distribution shift, the performance of deep learning-based method for image dehazing is adversely affected when applied to real-world hazy images. In this paper, we find that such deviation in dehazing task between real and synthetic domains may come from the imperfect collection of clean data. Owing to the complexity of the scene and the effect of depth, the collected clean data cannot strictly meet the ideal conditions, which makes the atmospheric physics model in the real domain inconsistent with that in the synthetic domain. For this reason, we come up with a synthetic-to-real dehazing method based on domain unification, which attempts to unify the relationship between the real and synthetic domain, thus to let the dehazing model more in line with the actual situation. Extensive experiments qualitatively and quantitatively demonstrate that the proposed dehazing method significantly outperforms state-of-the-art methods on real-world images.