Towards a Unified Approach to Single Image Deraining and Dehazing
This work addresses image restoration for rainy and hazy conditions, which is important for computer vision applications, but it is incremental as it builds upon existing models and networks.
The authors tackled the problem of single image deraining and dehazing by developing a new physical model for rain effects and proposing a Densely Scale-Connected Attentive Network (DSCAN), which delivered superior results on synthetic and real images compared to state-of-the-art methods.
We develop a new physical model for the rain effect and show that the well-known atmosphere scattering model (ASM) for the haze effect naturally emerges as its homogeneous continuous limit. Via depth-aware fusion of multi-layer rain streaks according to the camera imaging mechanism, the new model can better capture the sophisticated non-deterministic degradation patterns commonly seen in real rainy images. We also propose a Densely Scale-Connected Attentive Network (DSCAN) that is suitable for both deraining and dehazing tasks. Our design alleviates the bottleneck issue existent in conventional multi-scale networks and enables more effective information exchange and aggregation. Extensive experimental results demonstrate that the proposed DSCAN is able to deliver superior derained/dehazed results on both synthetic and real images as compared to the state-of-the-art. Moreover, it is shown that for our DSCAN, the synthetic dataset built using the new physical model yields better generalization performance on real images in comparison with the existing datasets based on over-simplified models.