https://scholars.lib.ntu.edu.tw/handle/123456789/581484
標題: | Learning to see through obstructions | 作者: | Liu Y.-L Lai W.-S Yang M.-H Huang J.-B. YUNG-YU CHUANG |
關鍵字: | Convolutional neural networks; Data transfer; Deep neural networks; Fences; Optical flows; Pattern recognition; Dense optical flow; Flow estimation; Learning-based approach; Moving cameras; Potential errors; Real images; Short sequences; Multilayer neural networks | 公開日期: | 2020 | 起(迄)頁: | 14203-14212 | 來源出版物: | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | 摘要: | We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera. Our method leverages the motion differences between the background and the obstructing elements to recover both layers. Specifically, we alternate between estimating dense optical flow fields of the two layers and reconstructing each layer from the flow-warped images via a deep convolutional neural network. The learning-based layer reconstruction allows us to accommodate potential errors in the flow estimation and brittle assumptions such as brightness consistency. We show that training on synthetically generated data transfers well to real images. Our results on numerous challenging scenarios of reflection and fence removal demonstrate the effectiveness of the proposed method. ?2020 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094626363&doi=10.1109%2fCVPR42600.2020.01422&partnerID=40&md5=1a4e4d90659dc46ea0a0f43e10663d39 https://scholars.lib.ntu.edu.tw/handle/123456789/581484 |
ISSN: | 10636919 | DOI: | 10.1109/CVPR42600.2020.01422 | SDG/關鍵字: | Convolutional neural networks; Data transfer; Deep neural networks; Fences; Optical flows; Pattern recognition; Dense optical flow; Flow estimation; Learning-based approach; Moving cameras; Potential errors; Real images; Short sequences; Multilayer neural networks |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。