Density-aware Single Image De-raining using a Multi-stream Dense Network
This addresses the challenge of image de-raining for computer vision applications, but it is incremental as it builds on existing CNN-based de-raining approaches with a focus on density estimation.
The paper tackles the problem of removing non-uniform rain streaks from single images by proposing DID-MDN, a density-aware multi-stream densely connected CNN that jointly estimates rain density and de-rains, achieving significant improvements over state-of-the-art methods on synthetic and real datasets.
Single image rain streak removal is an extremely challenging problem due to the presence of non-uniform rain densities in images. We present a novel density-aware multi-stream densely connected convolutional neural network-based algorithm, called DID-MDN, for joint rain density estimation and de-raining. The proposed method enables the network itself to automatically determine the rain-density information and then efficiently remove the corresponding rain-streaks guided by the estimated rain-density label. To better characterize rain-streaks with different scales and shapes, a multi-stream densely connected de-raining network is proposed which efficiently leverages features from different scales. Furthermore, a new dataset containing images with rain-density labels is created and used to train the proposed density-aware network. Extensive experiments on synthetic and real datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. In addition, an ablation study is performed to demonstrate the improvements obtained by different modules in the proposed method. Code can be found at: https://github.com/hezhangsprinter