Generalizing the Nonlocal-Means to Super-Resolution Reconstruction

Department of Computer Science, The Technion-Israel Institute of Technology, Haifa, Israel.
IEEE Transactions on Image Processing (Impact Factor: 3.63). 02/2009; 18(1):36-51. DOI: 10.1109/TIP.2008.2008067
Source: PubMed


Super-resolution reconstruction proposes a fusion of several low-quality images into one higher quality result with better optical resolution. Classic super-resolution techniques strongly rely on the availability of accurate motion estimation for this fusion task. When the motion is estimated inaccurately, as often happens for nonglobal motion fields, annoying artifacts appear in the super-resolved outcome. Encouraged by recent developments on the video denoising problem, where state-of-the-art algorithms are formed with no explicit motion estimation, we seek a super-resolution algorithm of similar nature that will allow processing sequences with general motion patterns. In this paper, we base our solution on the Nonlocal-Means (NLM) algorithm. We show how this denoising method is generalized to become a relatively simple super-resolution algorithm with no explicit motion estimation. Results on several test movies show that the proposed method is very successful in providing super-resolution on general sequences.

  • Source
    • "Reconstruction-based methods [10] [11] [12] [13] [14] [15] [16] [17] [18] impose certain prior knowledge to regularize this ill-posed problem so as to suppress artifacts and reach a solution that is more likely to be the natural image. Some of commonly used natural image priors include total-variation prior [10], gradient-profile prior [11] [12] [13] [14] and nonlocal similarity [15] [16] [17] [18]. Although the reconstruction-based methods can generate sharp edges, the details of the HR image cannot be restored especially for cases with large upscaling factors. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Sparse representation has been extensively studied for image super-resolution (SR) and achieved great improvement. Deep learning based SR methods have also emerged in the literature to pursue better SR results. In this paper, we propose to use a set of decision tree strategies for fast and high quality image SR. We take the divide-and-conquer strategy using decision tree for super-resolution (SRDT) which performs a few simple binary tests to classify an input LR patch into one of the leaf nodes and directly multiplies this LR patch with the regression model at that leaf node for regression. Both the classification process and the regression process take extremely small amount of computation. We formulate a hierarchical decision trees (SRHDT) method which cascades multiple layers of super-resolution decision trees to further boost the SR results. Inspired by the random forests approach which combines regression models from an ensemble of decision trees, we propose a hierarchical decision trees with fused regression model (SRHDT_f) which can fuse the regression models from up to 8 relevant leaf nodes within the same decision tree to form a more robust one and achieves another 0.1 dB improvement. Our experimental results show that our initial approach, the SRDT method achieves comparable SR results as the sparse representation based method and the deep learning based method but the speed of ours method is much faster. Furthermore, our enhanced version, the SRHDT_f method achieves more than 0.3 dB higher PSNR over that of the A+ method which is the state-of-the-art method in SR.
    Full-text · Article · Dec 2015 · IEEE Transactions on Circuits and Systems for Video Technology
  • Source
    • "Reconstruction stage combines information from the series of registered images into a single image with more definition and quality (Kang & Chaudhuri, 2003; Yang & Huang, 2010). Buades et al. (2005) proposed the nonlocal means (NLM) denoising algorithm and Protter et al. (2009) adapted the method for SR purposes, showing a very robust behaviour against inaccuracies in registration and motion tracking, as well as in electron microscopy images (Binev et al., 2012; Mevenkamp et al., 2014). NLM assumes that image content is likely to repeat itself within some neighbourhood; therefore the algorithm calculates a weighted averaging on those pixels in the same patch (search window) whose intensity distributions are close to each other, in terms of the Euclidean distance. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Super-resolution (SR) software-based techniques aim at generating a final image by combining several noisy frames with lower resolution from the same scene. A comparative study on high-resolution high-angle annular dark field images of InAs/GaAs QDs has been carried out in order to evaluate the performance of the SR technique. The obtained SR images present enhanced resolution and higher signal-to-noise (SNR) ratio and sharpness regarding the experimental images. In addition, SR is also applied in the field of strain analysis using digital image processing applications such as geometrical phase analysis and peak pairs analysis. The precision of the strain mappings can be improved when SR methodologies are applied to experimental images.
    Full-text · Article · Oct 2015 · Journal of Microscopy
  • Source
    • "For a given unknown image patch, many similar patches which are either close or far to this patch might be found. This type of nonlocal similarity has been effectively used in image de-noising [20] [21] [22] [23], de-blurring [24] [25] and super resolution [26] [27]. NARM aims to model a given pixel as the linear combination of its nonlocal neighbouring pixels. "

    Preview · Article · Feb 2015
Show more