Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising

By Yi Peng, Deyu Meng, Zongben Xu, Chenqiang Gao, Yi Yang, Biao Zhang. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

339 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Kronecker-Basis-Representation Based Tensor Sparsity and Its Applications to Tensor Recovery (2018, background): “…state-of-the-arts for 2D extended band-wise meth-ods; 3D-cube K-SVD [18], 5 ANLM3D [46] 6 and BM4D [44], [45], 7 representing state-of-the-arts for 2D extended 3D-cube-based methods; LRTA [49], PARAFAC [41], 8 TDL [52], 9 t-SVD [74] 10 (using the same denoising framework as shown in Fig.”
High-quality hyperspectral reconstruction using a spectral prior (2017, methodology): “However, instead of using predetermined bases (such as discrete cosine transforms or wavelets) or dictionary-based sparse coding [Lin et al. 2014; Peng et al. 2014; Wang et al. 2015], we rely on the convolutional autoencoder to decompose input signals into a set of basis vectors and coefficients.”
Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition (2017, methodology): “D ﬁltering (BM4D) [43], and the decomposable nonlocal tensor dictionary learning (TDL) [33].”
Hyperspectral Image Super-Resolution via Non-local Sparse Tensor Factorization (2017, methodology): “In the past years, tensor factorization has been successfully applied into multiframe data denoising [10, 21], completion [41, 17, 40], compressive sensing [36] and classification [35].”