I Can See Clearly Now : Image Restoration via De-Raining
This addresses image restoration for autonomous driving and computer vision systems operating in rainy conditions, though it's an incremental improvement combining existing techniques with new data.
The paper tackles the problem of image degradation caused by rain droplets and streaks, presenting a method that improves segmentation tasks by removing these artifacts. Results show significant improvement on road marking segmentation (CamVid), semantic segmentation (Cityscapes), and a custom real-rain dataset.
We present a method for improving segmentation tasks on images affected by adherent rain drops and streaks. We introduce a novel stereo dataset recorded using a system that allows one lens to be affected by real water droplets while keeping the other lens clear. We train a denoising generator using this dataset and show that it is effective at removing the effect of real water droplets, in the context of image reconstruction and road marking segmentation. To further test our de-noising approach, we describe a method of adding computer-generated adherent water droplets and streaks to any images, and use this technique as a proxy to demonstrate the effectiveness of our model in the context of general semantic segmentation. We benchmark our results using the CamVid road marking segmentation dataset, Cityscapes semantic segmentation datasets and our own real-rain dataset, and show significant improvement on all tasks.