scispace - formally typeset
Search or ask a question
Topic

Upsampling

About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: Zhang et al. as discussed by the authors proposed a green channel prior (GCP) to guide the feature extraction and feature upsampling of the whole image for joint denoising and demosaicing.
Abstract: Denoising and demosaicking are essential yet correlated steps to reconstruct a full color image from the raw color filter array (CFA) data. By learning a deep convolutional neural network (CNN), significant progress has been achieved to perform denoising and demosaicking jointly. However, most existing CNN-based joint denoising and demosaicking (JDD) methods work on a single image while assuming additive white Gaussian noise, which limits their performance on real-world applications. In this work, we study the JDD problem for real-world burst images, namely JDD-B. Considering the fact that the green channel has twice the sampling rate and better quality than the red and blue channels in CFA raw data, we propose to use this green channel prior (GCP) to build a GCP-Net for the JDD-B task. In GCP-Net, the GCP features extracted from green channels are utilized to guide the feature extraction and feature upsampling of the whole image. To compensate for the shift between frames, the offset is also estimated from GCP features to reduce the impact of noise. Our GCP-Net can preserve more image structures and details than other JDD methods while removing noise. Experiments on synthetic and real-world noisy images demonstrate the effectiveness of GCP-Net quantitatively and qualitatively.

27 citations

Proceedings ArticleDOI
16 Apr 2012
TL;DR: This work proposes cross-correlation via sparse representation: a new framework for ranging based on l1-minimization, which shows that the proposed framework, together with the proposed correlation domain achieved up to two order of magnitude better performance compared to naive approaches such as working on DCT domain and downsampling.
Abstract: Cross-correlation is a popular signal processing technique used in numerous localization and tracking systems for ob-taining reliable range information. However, a practical efficient implementation has not yet been achieved on resource constrained wireless sensor network platforms. We propose cross-correlation via sparse representation: a new framework for ranging based on l1-minimization. The key idea is to compress the signal samples on the mote platform by efficient random projections and transfer them to a central device, where a convex optimization process estimates the range by exploiting its sparsity in our proposed correlation domain. Through sparse representation theory validation, extensive empirical studies and experiments on an end-to-end acoustic ranging system implemented on resource limited off-the-shelf sensor nodes, we show that the proposed framework, together with the proposed correlation domain achieved up to two order of magnitude better performance compared to naive approaches such as working on DCT domain and downsampling. Furthermore, compared to cross-correlation results, 30–40% measurements are sufficient to obtain precise range estimates with an additional bias of only 2–6 cm for high accuracy application requirements, while 5% measurements are adequate to achieve approximately 100 cm precision for lower accuracy applications.

27 citations

Journal ArticleDOI
TL;DR: A novel single anisotropic 3-D MR image upsampling method via sparse representation and overcomplete dictionary that is trained from in-plane high resolution slices to upsample in the out-of-plane dimensions that is more accurate than classical interpolation and does not require extra training sets.
Abstract: In magnetic resonance (MR), hardware limitation, scanning time, and patient comfort often result in the acquisition of anisotropic 3-D MR images. Enhancing image resolution is desired but has been very challenging in medical image processing. Super resolution reconstruction based on sparse representation and overcomplete dictionary has been lately employed to address this problem; however, these methods require extra training sets, which may not be always available. This paper proposes a novel single anisotropic 3-D MR image upsampling method via sparse representation and overcomplete dictionary that is trained from in-plane high resolution slices to upsample in the out-of-plane dimensions. The proposed method, therefore, does not require extra training sets. Abundant experiments, conducted on simulated and clinical brain MR images, show that the proposed method is more accurate than classical interpolation. When compared to a recent upsampling method based on the nonlocal means approach, the proposed method did not show improved results at low upsampling factors with simulated images, but generated comparable results with much better computational efficiency in clinical cases. Therefore, the proposed approach can be efficiently implemented and routinely used to upsample MR images in the out-of-planes views for radiologic assessment and postacquisition processing.

27 citations

Journal ArticleDOI
TL;DR: Experimental results compared with existing interpolation methods demonstrate that the proposed iterative multiscale semilocal interpolation method can not only substantially alleviate the aliasing problem but also produce better results across a wide range of scenes both in terms of quantitative evaluation and subjective visual quality.
Abstract: Aliasing is a common artifact in low-resolution (LR) images generated by a downsampling process. Recovering the original high-resolution image from its LR counterpart while at the same time removing the aliasing artifacts is a challenging image interpolation problem. Since a natural image normally contains redundant similar patches, the values of missing pixels can be available at texture-relevant LR pixels. Based on this, we propose an iterative multiscale semilocal interpolation method that can effectively address the aliasing problem. The proposed method estimates each missing pixel from a set of texture-relevant semilocal LR pixels with the texture similarity iteratively measured from a sequence of patches of varying sizes. Specifically, in each iteration, top texture-relevant LR pixels are used to construct a data fidelity term in a maximum a posteriori estimation, and a bilateral total variation is used as the regularization term. Experimental results compared with existing interpolation methods demonstrate that our method can not only substantially alleviate the aliasing problem but also produce better results across a wide range of scenes both in terms of quantitative evaluation and subjective visual quality.

27 citations

Patent
10 Jul 2003
TL;DR: An interpolating sample rate converter that provides rate conversion by a factor of M/N comprising an upsampler that upsamples an input data stream, a filter that shapes the upsampled data stream in accordance with a predetermined power spectrum, and a downsampler, which downsamples the upampled and shaped signal by N to produce an output data stream is presented in this article.
Abstract: An interpolating sample rate converter that provides rate conversion by a factor of M/N comprising: an upsampler that upsamples an input data stream by a factor of M; a filter that shapes the upsampled data stream in accordance with a predetermined power spectrum; and a downsampler that downsamples the upsampled and shaped signal by a factor of N to produce an output data stream; wherein the upsampler and filter are implemented, at least in part, by a cascaded integrator-comb filter; and wherein the upsampling factor M is a natural number and the downsampling factor N is a rational number but not necessarily a natural number.

27 citations


Network Information
Related Topics (5)
Convolutional neural network
74.7K papers, 2M citations
90% related
Image segmentation
79.6K papers, 1.8M citations
90% related
Feature extraction
111.8K papers, 2.1M citations
89% related
Deep learning
79.8K papers, 2.1M citations
88% related
Feature (computer vision)
128.2K papers, 1.7M citations
87% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023469
2022859
2021330
2020322
2019298
2018236