![]() Levin, A., Fergus, R., Durand, F., Freeman, W.T.: Image and depth from a conventional camera with a coded aperture. Lai, W., Ding, J., Lin, Y., Chuang, Y.: Blur kernel estimation using normalized color-line priors. Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. Köhler, R., Hirsch, M., Mohler, B., Schölkopf, B., Harmeling, S.: Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database. Hu, Z., Yang, M.H.: Good regions to deblur. Hu, Z., Cho, S., Wang, J., Yang, M.H.: Deblurring low-light images with light streaks. In: International Joint Conference on Artificial Intelligence (2017) Guo, X., Lin, Z.: ROUTE: robust outlier estimation for low rank matrix recovery. Gong, D., Tan, M., Zhang, Y., van den Hengel, A., Shi, Q.: Blind image deconvolution by automatic gradient activation. In: ECCV (2018)įergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: Removing camera shake from a single photograph. In: IEEE ICCV (2017)ĭong, J., Pan, J., Sun, D., Su, Z., Yang, M.: Learning data terms for non-blind deblurring. In: IEEE ICCV (2011)ĭong, J., Pan, J., Su, Z., Yang, M.H.: Blind image deblurring with outlier handling. 28(5), 145 (2009)Ĭho, S., Wang, J., Lee, S.: Handling outliers in non-blind image deconvolution. In: IEEE CVPR (2019)Ĭho, S., Lee, S.: Fast motion deblurring. 70(3), 279–298 (2006)Ĭhen, L., Fang, F., Wang, T., Zhang, G.: Blind image deblurring with local maximum gradient prior. ![]() Keywordsīar, L., Kiryati, N., Sochen, N.: Image deblurring in the presence of impulsive noise. Extensive experiments demonstrate the superiority of OID against recent works both quantitatively and qualitatively. OID is easy to implement and extendable for non-blind restoration. Unlike previous indirect outlier processing methods, OID tackles outliers directly by explicitly identifying and discarding them, when updating both the latent image and the blur kernel during the deblurring process, where the outliers are detected by using the sparse and entropy-based modules. To address these problems, this paper develops a simple yet effective Outlier Identifying and Discarding (OID) method, which alleviates limitations in existing Maximum A Posteriori (MAP)-based deblurring models when significant outliers are presented. However, these indirect approaches may fail when massive outliers are presented, since informative details may be polluted by outliers or erased during the pre-processing steps. Prior arts develop sophisticated edge-selecting steps or noise filtering pre-processing steps to deal with outliers (i.e. Even a small amount of outliers can dramatically degrade the quality of the estimated blur kernel, because the outliers are not conforming to the linear formation of the blurring process. Blind deblurring methods are sensitive to outliers, such as saturated pixels and non-Gaussian noise. ![]()
0 Comments
Leave a Reply. |