Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network

详细信息    查看全文

• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9908
• 期：1
• 页码：560-576
• 全文大小：4,518 KB
• 参考文献：1.Deriche, R.: Recursively implementating the Gaussian and its derivatives. Ph.D. thesis, INRIA (1993)
  2.Young, I.T., Vliet, L.J.V.: Recursive implementation of the gaussian filter. Sig. Process. 44(2), 139–151 (1995)CrossRef
  3.Tan, S., Dale, J.L., Johnston, A.: Performance of three recursive algorithms for fast space-variant gaussian filtering. Real-Time Imaging 9(3), 215–228 (2003)CrossRef
  4.Yang, Q.: Recursive bilateral filtering. In: ECCV
  5.Gastal, E.S., Oliveira, M.M.: Domain transform for edge-aware image and video processing. ACM TOG 30, 69 (2011)CrossRef
  6.Xu, L., Ren, J.S., Liu, C., Jia, J.: Deep convolutional neural network for image deconvolution. In: NIPS, pp. 1790–1798 (2014)
  7.Xu, L., Ren, J.S., Yan, Q., Liao, R., Jia, J.: Deep edge-aware filters. In: ICML, pp. 1669–1678 (2015)
  8.Sj, R.J., Li, X., Qiong, Y., Wenxiu, S.: Shepard convolutional neural networks. In: NIPS, pp. 901–909 (2015)
  9.Ren, J.S.J., Xu, L.: On vectorization of deep convolutional neural networks for vision tasks. In: AAAI, pp. 1840–1846 (2015)
  10.Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: ECCV, pp. 184–199 (2014)
  11.Xu, L., Yan, Q., Xia, Y., Jia, J.: Structure extraction from texture via relative total variation. ACM TOG 31(6), 139 (2012)
  12.Graves, A., Fernndez, S., Schmidhuber, J.: Multi-dimensional recurrent neural networks. In: ICANN (2007)
  13.Byeon, W., Breuel, T.M., Raue, F., Liwicki, M.: Scene labeling with LSTM recurrent neural networks. In: CVPR, pp. 3547–3555 (2015)
  14.Visin, F., Kastner, K., Cho, K., Matteucci, M., Courville, A., Bengio, Y.: Renet: a recurrent neural network based alternative to convolutional networks. arXiv preprint arXiv:​1505.​00393 (2015)
  15.Oord, A.V.D., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. arXiv preprint arXiv:​1601.​06759 (2016)
  16.Stollenga, M.F., Byeon, W., Liwicki, M., Schmidhuber, J.: Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. arXiv preprint arXiv:​1506.​07452 (2015)
  17.Kalchbrenner, N., Danihelka, I., Graves, A.: Grid long short-term memory. arXiv preprint arXiv:​1507.​01526 (2015)
  18.Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: ICCV, pp. 839–846 (1998)
  19.He, K., Sun, J., Tang, X.: Guided image filtering. IEEE PAMI 35(6), 1397–1409 (2013)CrossRef
  20.Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM TOG 27, 67 (2008)CrossRef
  21.Weickert, J.: Anisotropic Diffusion in Image Processing. B.G Teubner Stuttgart, Stuttgart (1998)MATH
  22.Levin, A., Lischinski, D., Weiss, Y.: Colorization using optimization. ACM TOG 23(3), 689–694 (2004)CrossRef
  23.Xu, L., Yan, Q., Jia, J.: A sparse control model for image and video editing. ACM TOG 32(6), 197:1–197:10 (2013)
  24.Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE PAMI 30(2), 228–242 (2008)CrossRef
  25.Burger, H.C., Schuler, C.J., Harmeling, S.: Image denoising: can plain neural networks compete with bm3d? In: CVPR, pp. 2392–2399 (2012)
  26.Xie, J., Xu, L., Chen, E.: Image denoising and inpainting with deep neural networks. In: NIPS, pp. 341–349 (2012)
  27.Agostinelli, F., Anderson, M.R., Lee, H.: Adaptive multi-column deep neural networks with application to robust image denoising. In: NIPS, pp. 1493–1501 (2013)
  28.John, G.P., Dimitris, G.M.: Digital Signal Processing, Principles, Algorithms, and Applications. Prentice Hall, Upper Saddle River (1996)
  29.Gastal, E.S., Oliveira, M.M.: High-order recursive filtering of non-uniformly sampled signals for image and video processing. Comput. Graph. Forum 34, 81–93 (2015)CrossRef
  30.Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: NIPS (2009)
  31.Chen, L., Barron, J.T., Papandreou, G., Murphy, K., Yuille, A.L.: Semantic image segmentation with task-specific edge detection using CNNS and a discriminatively trained domain transform. arXiv preprint arXiv:​1511.​03328 (2015)
  32.Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)
  33.Lin, T., Maire, M., Belongie, S., Bourdev, L.D., Girshick, R.B., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context (2014)
  34.Xu, L., Lu, C., Xu, Y., Jia, J.: Image smoothing via l-0 gradient minimization. ACM TOG 30, 174 (2011)
  35.Zhang, Q., Xu, L., Jia, J.: 100+ times faster weighted median filter (WMF). In: CVPR, pp. 2830–2837 (2014)
  36.Zhang, Q., Shen, X., Xu, L., Jia, J.: Rolling guidance filter. In: ECCV, pp. 815–83 (2014)
  37.Osher, S., Rudin, L.I.: Feature-oriented image enhancement using shock filters. SIAM J. Numer. Anal. 27(4), 919–940 (1990)CrossRef MATH
  38.Karacan, L., Erdem, E., Erdem, A.: Structure-preserving image smoothing via region covariances. ACM TOG 32, 176 (2013)CrossRef
  39.Paris, S., Hasinoff, S.W., Kautz, J.: Local laplacian filters: edge-aware image processing with a laplacian pyramid. ACM Trans. Graph. 30(4), 68 (2011)CrossRef
  40.Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: ICCV, pp. 479–486 (2011)
  
• 作者单位：Sifei Liu (17)
  Jinshan Pan (17) (18)
  Ming-Hsuan Yang (17)
  
  17. UC Merced, Merced, USA
  18. Dalian University of Technology, Dalian, China
  
• 丛书名：Computer Vision ¨C ECCV 2016
• ISBN：978-3-319-46493-0
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9908

文摘

In this paper, we consider numerous low-level vision problems (e.g., edge-preserving filtering and denoising) as recursive image filtering via a hybrid neural network. The network contains several spatially variant recurrent neural networks (RNN) as equivalents of a group of distinct recursive filters for each pixel, and a deep convolutional neural network (CNN) that learns the weights of RNNs. The deep CNN can learn regulations of recurrent propagation for various tasks and effectively guides recurrent propagation over an entire image. The proposed model does not need a large number of convolutional channels nor big kernels to learn features for low-level vision filters. It is significantly smaller and faster in comparison with a deep CNN based image filter. Experimental results show that many low-level vision tasks can be effectively learned and carried out in real-time by the proposed algorithm.