2021/08/07 by Zifan Shi, Na Fan, Shi, Zifan +5 · 1 citation
Computer Science · #Advanced Neural Network Applications #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques #Machine Learning (cs.LG) #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2108.03457
openalex publication_date 2021/08/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Existing vision systems for autonomous driving or robots are sensitive to waterdrops adhered to windows or camera lenses. Most recent waterdrop removal approaches take a single image as input and often fail to recover the missing content behind waterdrops faithfully. Thus, we propose a learning-based model for waterdrop removal with stereo images. To better detect and remove waterdrops from stereo images, we propose a novel row-wise dilated attention module to enlarge attention's receptive field for effective information propagation between the two stereo images. In addition, we propose an attention consistency loss between the ground-truth disparity map and attention scores to enhance the left-right consistency in stereo images. Because of related datasets' unavailability, we collect a real-world dataset that contains stereo images with and without waterdrops. Extensive experiments on our dataset suggest that our model outperforms state-of-the-art methods both quantitatively and qualitatively. Our source code and the stereo waterdrop dataset are available at \hrefhttps://github.com/VivianSZF/Stereo-Waterdrop-Removalhttps://github.com/VivianSZF/Stereo-Waterdrop-Removal