Heavy-Tailed Self-Similarity Modeling for Single Image Super Resolution

Chantas, Giannis; Nikolopoulos, Spiros; Kompatsiaris, Ioannis

doi:10.1109/tip.2020.3038521

Cited by 17 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effectiveness of the proposed method, extensive qualitative and quantitative experiments are performed on the real-world ISAR images. Seven state-of-the-art approaches are selected as reference: Expected Patch Log Likelihood (EPLL), 27 Non-Local Means (NL-Means), 28 Block-Matching and 3D Filtering (BM3D), 29 Non-Local Bayes (NL Bayes), 30 Bayes Least Squares-Gaussian Scale Mixtures (BLS-GSM), 31 Discrete Cosine Transform (DCT) 25 and Multiscale DCT (MSDCT). 32 3.1 | Implementation details and noisy ISAR image data…”

Section: Resultsmentioning

confidence: 99%

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

Xue

Feng

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Most existing nonblind denoising approaches assumed the noise to be homogeneous white Gaussian distribution with known intensity. However, it is difficult to know beforehand or model accurately real‐world noises with complex hybrid distribution and noise intensity. In this paper, active joint prior learning (JPL) is proposed for real‐world ISAR image blind denoising. (1) To explore strong model hierarchy and components relationship automatically, a novel graphical Dirichlet mixture process (GDMP) model is developed, where the latent representations and component hyperparameters are jointly learned from each other. (2) A multiscale joint learning strategy (MJLS) is proposed to take advantage of both the optimization‐ and discriminative learning‐based capabilities. The external noiseless, internal noisy image information and their relationships are jointly explored simultaneously. (3) Low‐rank weighted sparse learning (LWSL) is proposed to learn sparse discriminative correlation components for robust prior learning, and latent low‐rank embedding for GDMP patterns self‐adaptive inference. Extensive experimental results on ISAR image datasets demonstrate the effectiveness of the proposed model for both synthesis and real‐world noisy ISAR images, and the proposed method outperforms the state‐of‐the‐art denoising methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

Xue

Feng

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

show abstract

“…Another representative work by Huang et al [10] found more expressive self-exemplars by expanding the internal search space using geometric transformations. Chen et al [29] characterized self-similarity prior in the transform domain using the local structure-adaptive transform, while Chantas et al [30] introduced a variational approach with an observation that the self-similarity follows a heavy-tailed distribution.…”

Section: Self-similarity In Sisrmentioning

confidence: 99%

RZSR: Reference-Based Zero-Shot Super-Resolution With Depth Guided Self-Exemplars

Yoo

Kim

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Recent methods for single image super-resolution (SISR) have demonstrated outstanding performance in generating high-resolution (HR) images from low-resolution (LR) images. However, most of these methods show their superiority using synthetically generated LR images, and their generalizability to real-world images is often not satisfactory. In this paper, we pay attention to two well-known strategies developed for robust superresolution (SR), i.e., reference-based SR (RefSR) and zero-shot SR (ZSSR), and propose an integrated solution, called referencebased zero-shot SR (RZSR). Following the principle of ZSSR, we train an image-specific SR network at test time using training samples extracted only from the input image itself. To advance ZSSR, we obtain reference image patches with rich textures and high-frequency details which are also extracted only from the input image using cross-scale matching. To this end, we construct an internal reference dataset and retrieve reference image patches from the dataset using depth information. Using LR patches and their corresponding HR reference patches, we train a RefSR network that is embodied with a non-local attention module. Experimental results demonstrate the superiority of the proposed RZSR compared to the previous ZSSR methods and robustness to unseen images compared to other fully supervised SISR methods.

show abstract

“…f. FSRCNN [13] : An advanced and modified version of SRCNN with deeper architecture and transpose convolution approach. g. VBPS [52] : Recent method for image SR that exploits the inherent self-similarities found in images. Tables I and II report the PSNR and SSIM results of TTDSR and other methods, respectively.…”

Section: Comparative Analysismentioning

confidence: 99%

Tchebichef Transform Domain-based Deep Learning Architecture for Image Super-resolution

Kumar¹,

Singh²

2021

Preprint

View full text Add to dashboard Cite

The recent outbreak of COVID-19 has motivated researchers to contribute in the area of medical imaging using artificial intelligence and deep learning. Super-resolution (SR), in the past few years, has produced remarkable results using deep learning methods. The ability of deep learning methods to learn the non-linear mapping from low-resolution (LR) images to their corresponding high-resolution (HR) images leads to compelling results for SR in diverse areas of research. In this paper, we propose a deep learning based image superresolution architecture in Tchebichef transform domain. This is achieved by integrating a transform layer into the proposed architecture through a customized Tchebichef convolutional layer (T CL). The role of T CL is to convert the LR image from the spatial domain to the orthogonal transform domain using Tchebichef basis functions. The inversion of the aforementioned transformation is achieved using another layer known as the Inverse Tchebichef convolutional Layer (IT CL), which converts back the LR images from the transform domain to the spatial domain. It has been observed that using the Tchebichef transform domain for the task of SR takes the advantage of high and lowfrequency representation of images that makes the task of superresolution simplified. We, further, introduce transfer learning approach to enhance the quality of Covid based medical images. It is shown that our architecture enhances the quality of Xray and CT images of COVID-19, providing a better image quality that helps in clinical diagnosis. Experimental results obtained using the proposed Tchebichef transform domain superresolution (TTDSR) architecture provides competitive results when compared with most of the deep learning methods employed using a fewer number of trainable parameters.

show abstract

Heavy-Tailed Self-Similarity Modeling for Single Image Super Resolution

Cited by 17 publications

References 47 publications

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

RZSR: Reference-Based Zero-Shot Super-Resolution With Depth Guided Self-Exemplars

Tchebichef Transform Domain-based Deep Learning Architecture for Image Super-resolution

Contact Info

Product

Resources

About