https://scholars.lib.ntu.edu.tw/handle/123456789/581092
標題: | Two-Way Recursive Filtering | 作者: | Tu W Chien S. SHAO-YI CHIEN |
關鍵字: | Backpropagation; Deep neural networks; Iterative methods; Multilayer neural networks; Connection schemes; Image filtering; Image filters; Image smoothing; Receptive fields; Recursive filtering; Recursive filters; Refinement algorithms; Pixels | 公開日期: | 2021 | 來源出版物: | IEEE Transactions on Circuits and Systems for Video Technology | 摘要: | We present a new way of recursive image filtering called the two-way recursive filtering. Different from most recursive image filters that pose the 2D image filtering as iterative 1D row/column filtering, we consider the propagation on a 2D image plane directly. To compute the filtered value of a pixel, our method takes feedback from two neighboring pixels, one connected horizontally and the other connected vertically. In this way, the proposed filter has a dense receptive field, leading to fewer iterations needed to filter an image. We demonstrate its ability in high-quality edge-aware image smoothing without compromising the efficiency compared to 1D filters. We show that the proposed filter can also be formulated as a layer in a deep neural network. The feedback coefficients of the recursive filter are learned via backpropagating through the proposed filter. Our experiments on segmentation refinement show that our method produces favorable results against the three-way connection scheme in a previous segmentation refinement algorithm. To the best of our knowledge, this is the first work that explores the two-way pixel connectivity for recursive filtering. IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099584607&doi=10.1109%2fTCSVT.2021.3049833&partnerID=40&md5=68c9e946b3a548582b53d744cddcab8f https://scholars.lib.ntu.edu.tw/handle/123456789/581092 |
ISSN: | 10518215 | DOI: | 10.1109/TCSVT.2021.3049833 |
顯示於: | 電機工程學系 |
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。