2019/06/12 by Rajeev Yasarla, Vishal M. Patel, Yasarla, Rajeev +1 · 9 citations
Computer Science · Physics and Astronomy · #Color Science and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image Enhancement Techniques #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1906.11129
openalex publication_date 2019/06/12 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Single image de-raining is an extremely challenging problem since the rainy\nimage may contain rain streaks which may vary in size, direction and density.\nPrevious approaches have attempted to address this problem by leveraging some\nprior information to remove rain streaks from a single image. One of the major\nlimitations of these approaches is that they do not consider the location\ninformation of rain drops in the image. The proposed Uncertainty guided\nMulti-scale Residual Learning (UMRL) network attempts to address this issue by\nlearning the rain content at different scales and using them to estimate the\nfinal de-rained output. In addition, we introduce a technique which guides the\nnetwork to learn the network weights based on the confidence measure about the\nestimate. Furthermore, we introduce a new training and testing procedure based\non the notion of cycle spinning to improve the final de-raining performance.\nExtensive experiments on synthetic and real datasets to demonstrate that the\nproposed method achieves significant improvements over the recent\nstate-of-the-art methods. Code is available at:\nhttps://github.com/rajeevyasarla/UMRL--using-Cycle-Spinning\n