IMT Institutional Repository: No conditions. Results ordered -Date Deposited. 2024-03-29T10:52:37ZEPrintshttp://eprints.imtlucca.it/images/logowhite.pnghttp://eprints.imtlucca.it/2014-12-11T11:38:40Z2014-12-11T11:38:40Zhttp://eprints.imtlucca.it/id/eprint/2417This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/24172014-12-11T11:38:40ZSingle-image super-resolution via linear mapping of interpolated self-examplesThis paper presents a novel example-based single-image superresolution procedure that upscales to high-resolution (HR) a given low-resolution (LR) input image without relying on an external dictionary of image examples. The dictionary instead is built from the LR input image itself, by generating a double pyramid of recursively scaled, and subsequently interpolated, images, from which self-examples are extracted. The upscaling procedure is multipass, i.e., the output image is constructed by means of gradual increases, and consists in learning special linear mapping functions on this double pyramid, as many as the number of patches in the current image to upscale. More precisely, for each LR patch, similar self-examples are found, and, because of them, a linear function is learned to directly map it into its HR version. Iterative back projection is also employed to ensure consistency at each pass of the procedure. Extensive experiments and comparisons with other state-of-the-art methods, based both on external and internal dictionaries, show that our algorithm can produce visually pleasant upscalings, with sharp edges and well reconstructed details. Moreover, when considering objective metrics, such as Peak signal-to-noise ratio and Structural similarity, our method turns out to give the best performance.Marco Bevilacquamarco.bevilacqua@imtlucca.itAline RoumyChristine GuillemotMarie Line Alberi-Morel2014-12-11T11:31:01Z2014-12-11T11:31:01Zhttp://eprints.imtlucca.it/id/eprint/2416This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/24162014-12-11T11:31:01ZVideo super-resolution via sparse combinations of key-frame patches in a compression contextIn this paper we present a super-resolution (SR) method for upscaling low-resolution (LR) video sequences, that relies on the presence of periodic high-resolution (HR) key frames, and validate it in the context of video compression. For a given LR intermediate frame, the HR details are retrieved patch-by-patch by taking sparse linear combinations of patches found in the neighbor key frames. The performance of the video SR algorithm is assessed in a scheme where only some key frames from an original HR sequence are directly encoded; the remaining intermediate frames are down-sampled to LR and encoded as well, with a possibly different quantization parameter. SR is then finally employed to upscale these frames. For comparison, we consider the best case where the whole original HR sequence is encoded. With respect to this case, our SR-based approach is shown to bring a certain gain for low bit-rates (consistent when all frames are encoded independently), i.e. when a poor encoding can actually benefit of the special processing of the intermediate frames, so proving that video SR can be an useful tool in realistic scenarios.Marco Bevilacquamarco.bevilacqua@imtlucca.itAline RoumyChristine GuillemotMarie Line Alberi-Morel2014-12-11T11:25:26Z2014-12-11T11:34:03Zhttp://eprints.imtlucca.it/id/eprint/2415This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/24152014-12-11T11:25:26ZK-WEB: Nonnegative dictionary learning for sparse image representationsThis paper presents a new nonnegative dictionary learning method, to decompose an input data matrix into a dictionary of nonnegative atoms, and a representation matrix with a strict ℓ0-sparsity constraint. This constraint makes each input vector representable by a limited combination of atoms. The proposed method consists of two steps which are alternatively iterated: a sparse coding and a dictionary update stage. As for the dictionary update, an original method is proposed, which we call K-WEB, as it involves the computation of k WEighted Barycenters. The so designed algorithm is shown to outperform other methods in the literature that address the same learning problem, in different applications, and both with synthetic and “real” data, i.e. coming from natural images.Marco Bevilacquamarco.bevilacqua@imtlucca.itAline RoumyChristine GuillemotMarie Line Alberi-Morel2014-12-11T11:14:47Z2014-12-11T11:33:33Zhttp://eprints.imtlucca.it/id/eprint/2414This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/24142014-12-11T11:14:47ZSuper-resolution using neighbor embedding of back-projection residualsIn this paper we present a novel algorithm for neighbor embedding based super-resolution (SR), using an external dictionary. In neighbor embedding based SR, the dictionary is trained from couples of high-resolution and low-resolution (LR) training images, and consists of pairs of patches: matching patches (m-patches), which are used to match the input image patches and contain only low-frequency content, and reconstruction patches (r-patches), which are used to generate the output image patches and actually bring the high-frequency details. We propose a novel training scheme, where the m-patches are extracted from enhanced back-projected interpolations of the LR images and the r-patches are extracted from the back-projection residuals. A procedure to further optimize the dictionary is followed, and finally nonnegative neighbor embedding is considered at the SR algorithm stage. We consider singularly the various elements of the algorithm, and prove that each of them brings a gain on the final result. The complete algorithm is then compared to other state-of-the-art methods, and its competitiveness is shown.Marco Bevilacquamarco.bevilacqua@imtlucca.itAline RoumyChristine GuillemotMarie Line Alberi-Morel2014-12-11T11:06:46Z2014-12-11T11:33:08Zhttp://eprints.imtlucca.it/id/eprint/2413This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/24132014-12-11T11:06:46ZCompact and coherent dictionary construction for example-based super-resolutionThis paper presents a new method to construct a dictionary for example-based super-resolution (SR) algorithms. Example-based SR relies on a dictionary of correspondences of low-resolution (LR) and high-resolution (HR) patches. Having a fixed, prebuilt, dictionary, allows to speed up the SR process; however, in order to perform well in most cases, we need to have big dictionaries with a large variety of patches. Moreover, LR and HR patches often are not coherent, i.e. local LR neighborhoods are not preserved in the HR space. Our designed dictionary learning method takes as input a large dictionary and gives as an output a dictionary with a “sustainable” size, yet presenting comparable or even better performance. It firstly consists of a partitioning process, done according to a joint k-means procedure, which enforces the coherence between LR and HR patches by discarding those pairs for which we do not find a common cluster. Secondly, the clustered dictionary is used to extract some salient patches that will form the output set.Marco Bevilacquamarco.bevilacqua@imtlucca.itAline RoumyChristine GuillemotMarie Line Alberi-Morel2014-12-11T11:00:13Z2014-12-16T14:34:53Zhttp://eprints.imtlucca.it/id/eprint/2412This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/24122014-12-11T11:00:13ZLow-complexity single-image super-resolution based on nonnegative neighbor embeddingThis paper describes a single-image super-resolution (SR) algorithm based on nonnegative neighbor embedding. It belongs to the family of single-image example-based
SR algorithms, since it uses a dictionary of low resolution (LR) and high resolution (HR) trained patch pairs to infer the unknown HR details. Each LR feature vector in the input
image is expressed as the weighted combination of its K nearest neighbors in the dictionary; the corresponding HR feature vector is reconstructed under the assumption that the local LR embedding is preserved. Three key aspects are introduced in order to build a low-complexity competitive algorithm: (i) a compact but efficient representation of the
patches (feature representation) (ii) an accurate estimation of the patches by their nearest neighbors (weight computation) (iii) a compact and already built (therefore external) dictionary, which allows a one-step upscaling. The neighbor embedding SR algorithm so designed is shown to give good visual results, comparable to other state-of-the-art methods, while presenting an appreciable reduction of the computational time.Marco Bevilacquamarco.bevilacqua@imtlucca.itAline RoumyChristine GuillemotMarie Line Alberi-Morel2014-12-11T10:26:16Z2014-12-11T11:31:46Zhttp://eprints.imtlucca.it/id/eprint/2411This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/24112014-12-11T10:26:16ZNeighbor embedding based single-image super-resolution using Semi-Nonnegative Matrix FactorizationThis paper describes a novel method for single-image super-resolution (SR) based on a neighbor embedding technique which uses Semi-Nonnegative Matrix Factorization (SNMF). Each low-resolution (LR) input patch is approximated by a linear combination of nearest neighbors taken from a dictionary. This dictionary stores low-resolution and corresponding high-resolution (HR) patches taken from natural images and is thus used to infer the HR details of the super-resolved image. The entire neighbor embedding procedure is carried out in a feature space. Features which are either the gradient values of the pixels or the mean-subtracted luminance values are extracted from the LR input patches, and from the LR and HR patches stored in the dictionary. The algorithm thus searches for the K nearest neighbors of the feature vector of the LR input patch and then computes the weights for approximating the input feature vector. The use of SNMF for computing the weights of the linear approximation is shown to have a more stable behavior than the use of LLE and lead to significantly higher PSNR values for the super-resolved images.Marco Bevilacquamarco.bevilacqua@imtlucca.itAline RoumyChristine GuillemotMarie Line Alberi-Morel