Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
This addresses the problem of efficient and robust dehazing for non-homogeneous scenes, which is incremental as it builds on existing CNN methods.
The paper tackles non-homogeneous image dehazing by proposing a fast deep multi-patch hierarchical network that aggregates features from multiple patches, achieving a model size of 21.7 MB and an average runtime of 0.0145s for HD images.
Recently, CNN based end-to-end deep learning methods achieve superiority in Image Dehazing but they tend to fail drastically in Non-homogeneous dehazing. Apart from that, existing popular Multi-scale approaches are runtime intensive and memory inefficient. In this context, we proposed a fast Deep Multi-patch Hierarchical Network to restore Non-homogeneous hazed images by aggregating features from multiple image patches from different spatial sections of the hazed image with fewer number of network parameters. Our proposed method is quite robust for different environments with various density of the haze or fog in the scene and very lightweight as the total size of the model is around 21.7 MB. It also provides faster runtime compared to current multi-scale methods with an average runtime of 0.0145s to process 1200x1600 HD quality image. Finally, we show the superiority of this network on Dense Haze Removal to other state-of-the-art models.