Stereo Waterdrop Removal with Row-wise Dilated Attention
Zifan Shi,Na Fan,Dit-Yan Yeung,Qifeng Chen,Zifan Shi,Na Fan,Dit-Yan Yeung,Qifeng Chen
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...
