Modeling deformable gradient compositions for single-image super-resolution

Zhu, Yu; Zhang, Yanning; Bonev, Boyan; Yuille, Alan

doi:10.1109/cvpr.2015.7299180

Cited by 31 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the obtained HR images are usually over-sharped or suffer from false artifacts due to the incorrect estimation of gradients. Zhu et al [47] propose a deformable gradient compositional model to represent the non-singular primitives as compositions of singular ones. Then they use the external gradient pattern information to predict the HR gradients.…”

Section: Gradient-based Super-resolutionmentioning

confidence: 99%

Deep Gradient Prior Regularized Robust Video Super-Resolution

Song¹,

Liu

2021

Electronics

View full text Add to dashboard Cite

This paper proposes a robust multi-frame video super-resolution (SR) scheme to obtain high SR performance under large upscaling factors. Although the reference low-resolution frames can provide complementary information for the high-resolution frame, an effective regularizer is required to rectify the unreliable information from the reference frames. As the high-frequency information is mostly contained in the image gradient field, we propose to learn the gradient-mapping function between the high-resolution (HR) and the low-resolution (LR) image to regularize the fusion of multiple frames. In contrast to the existing spatial-domain networks, we train a deep gradient-mapping network to learn the horizontal and vertical gradients. We found that adding the low-frequency information (mainly from the LR image) to the gradient-learning network can boost the performance of the network. A forward and backward motion field prior is used to regularize the estimation of the motion flow between frames. For robust SR reconstruction, a weighting scheme is proposed to exclude the outlier data. Visual and quantitative evaluations on benchmark datasets demonstrate that our method is superior to many state-of-the-art methods and can recover better details with less artifacts.

show abstract

Section: Gradient-based Super-resolutionmentioning

confidence: 99%

Deep Gradient Prior Regularized Robust Video Super-Resolution

Song¹,

Liu

2021

Electronics

View full text Add to dashboard Cite

show abstract

“…Tai et al [10] proposed an approach to combine edge-directed SR with detail from an image and texture examples. Zhu et al [11] proposed an SISR method based on gradient reconstruction by collecting a dictionary of gradient patterns. The edge distribution tends to depend heavily on the similarities between training and test datasets.…”

Section: A Related Workmentioning

confidence: 99%

Edge Profile Super Resolution

Lee

Yun

Kim³

2021

IEEE Access

View full text Add to dashboard Cite

The purpose of single-image super resolution (SISR) is to reconstruct an accurate highresolution image from a degraded low-resolution image. Owing to the lack of information in low-resolution images, SISR is a challenging problem. In particular, it is difficult to represent details, including highfrequency components, such as texture and structural information. We propose the edge profile superresolution (EPSR) method to preserve structural information and restore texture. EPSR is achieved by stacking modified fractal residual network (mFRN) structures hierarchically and repeatedly. Each mFRN is composed of many residual edge profile blocks (REPBs) that extract features and preserve the edge, structure, and texture information of the image. For implementing REPB, we design three main modules: Residual Efficient Channel Attention Block(RECAB) module, Edge Profile(EP) module, and Context Network(CN) module. By repeating the procedure in the mFRN structure, the EPSR method could be used to extract high-fidelity features, thus preventing texture loss and preserving the structure with appropriate sharpness. Experimental results show that EPSR achieves competitive performance against state-of-the-art methods in terms of the peak signal-to-noise ratio(PSNR) and structural similarity index measure(SSIM) evaluation metrics, as well as visual results.

show abstract

“…For example, Chang et al [37] simply concatenated the firstorder and second-order gradients for feature representation based on the luminance values of the pixels in the patch. Zhu et al [38] proposed a gradient-based super-resolution method to exploit more expressive information from the external gradient patterns. In addition, Ma et al [39] applied a first-order gradient to a generative adversarial network (GAN)-based method as structure guidance for super-resolution.…”

Section: Difference Curvature-based Branch (Dcb)mentioning

confidence: 99%

Difference Curvature Multidimensional Network for Hyperspectral Image Super-Resolution

Zhang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In recent years, convolutional-neural-network-based methods have been introduced to the field of hyperspectral image super-resolution following their great success in the field of RGB image super-resolution. However, hyperspectral images appear different from RGB images in that they have high dimensionality, implying a redundancy in the high-dimensional space. Existing approaches struggle in learning the spectral correlation and spatial priors, leading to inferior performance. In this paper, we present a difference curvature multidimensional network for hyperspectral image super-resolution that exploits the spectral correlation to help improve the spatial resolution. Specifically, we introduce a multidimensional enhanced convolution (MEC) unit into the network to learn the spectral correlation through a self-attention mechanism. Meanwhile, it reduces the redundancy in the spectral dimension via a bottleneck projection to condense useful spectral features and reduce computations. To remove the unrelated information in high-dimensional space and extract the delicate texture features of a hyperspectral image, we design an additional difference curvature branch (DCB), which works as an edge indicator to fully preserve the texture information and eliminate the unwanted noise. Experiments on three publicly available datasets demonstrate that the proposed method can recover sharper images with minimal spectral distortion compared to state-of-the-art methods. PSNR/SAM is 0.3–0.5 dB/0.2–0.4 better than the second best methods.

show abstract

Modeling deformable gradient compositions for single-image super-resolution

Cited by 31 publications

References 19 publications

Deep Gradient Prior Regularized Robust Video Super-Resolution

Deep Gradient Prior Regularized Robust Video Super-Resolution

Edge Profile Super Resolution

Difference Curvature Multidimensional Network for Hyperspectral Image Super-Resolution

Contact Info

Product

Resources

About