Search Results

Super-resolution (SR), aiming to super-resolve degraded low-resolution image to recover the corresponding high-resolution counterpart, is an important and challenging task in computer vision, and with various applications. The emergence of deep ...

• This paper provides a comprehensive survey on deep-learning-based super-resolution methods along with their applications and limitations.
• This paper categorizes the methods from an application perspective and a taxonomy is proposed.

Computerised recognition of low-resolution scene text images has been a persistent challenge. To improve the recognition performance, image quality enhancement via image super-resolution technology provides an intuitive solution. Typical deep ...

• A scene text image super-resolution method is proposed.
• A self-supervised memory learning strategy is designed.
• A spatial refinement block is designed.
• Character perceptual loss and boundary enhancement loss are integrated.

LiDAR super-resolution can improve the quality of point cloud data, which is critical for improving many downstream tasks such as object detection, identification, and tracking. Traditional LiDAR super-resolution models often struggle with issues ...

Real-world image super-resolution (RISR) aims to reconstruct high-resolution (HR) images from degraded low-resolution (LR) inputs, addressing challenges such as blurring, noise, and compression artifacts. Unlike conventional super-resolution (SR) ...

Transformer-based methods have demonstrated impressive performance in 4D light field (LF) super-resolution by effectively modeling long-range spatial-angular correlations, but their quadratic complexity hinders the efficient processing of high ...

Reducing latency is a roaring trend in recent super-resolution (SR) research. While recent progress exploits various convolutional blocks, attention modules, and backbones to unlock the full potentials of the convolutional neural network (ConvNet),...$$

Reference-based image super-resolution aims to improve the clarity of input low-resolution (LR) images by leveraging additional high-resolution reference (Ref) images. Although existing methods effectively address the problems associated with ...

Scene text image super-resolution (STISR) aims at enhancing the visual clarity of a low-resolution text image for human perception or tasks like text recognition. In recent STISR work, various visual and semantic clues of the text play a key role ...

Image super-resolution (SR) technology aims to enhance the resolution and improve the quality of images, and it has been widely used in face recognition, small target detection, medical imaging and remote sensing image analysis. Image quality ...

• A three-axis mutually supervised super-resolution (TaMS-SR) reconstruction method.
• A Depth-GAN for synthesizing intermediate slices.
• A supervised and unsupervised interactive learning approach to enhance the accuracy of synthetic ...

This study aims to enhance the resolution in the axial direction of rectal cancer magnetic resonance (MR) imaging scans to improve the accuracy of visual interpretation and quantitative analysis. MR imaging is a critical ...

Recently, deep learning techniques and deep neural networks have been extensively studied and widely applied to single-image super-resolution (SISR). Although super-resolution networks have shown their effectiveness, they still face issues of ...

Recently, remote sensing images have become popular in various tasks, including resource exploration. However, limited by hardware conditions and formation processes, the obtained remote sensing images often suffer from low-resolution problems. ...

• Global attention network for remote sensing fully utilizes long-range information.
• Global sparse attention network focuses on valid global data and reduces computation.
• Global sparse attention network improves the EDSR method with ...

In this paper, we consider the problem of joint delay-Doppler estimation in an automotive radar based on orthogonal time frequency space (OTFS) modulation. We propose a super-resolution estimation approach that operates in the continuous domain ...

• A super-resolution approach is proposed to estimate delay and Doppler parameters for OTFS-based automotive radar.
• An ADMM-based fast algorithm is proposed to accelerate computation.
• Numerical studies are conducted to validate the ...

In recent years, with the increase in the depth and width of convolutional neural networks, single image super-resolution (SISR) algorithms have made significant breakthroughs in objective quantitative metrics and subjective visual quality. ...

• Propose HSNet that outperforms other SOTA lightweight SR methods.
• Design HDGP by utilizing hash coding to direct non-local attention.
• Design SCMF to combine multi-level feature fusion and pixel attention.

Hyperspectral (HS) image always suffers from the deficiency of low spatial resolution, compared with conventional optical image types, which has limited its further applications in remote sensing areas. Therefore, HS image super-resolution (SR) ...

• A transposed convolutional bi-directional LSTM SR network is constructed for HS image.
• The network aims at modeling the spatial–sequential correlated features of HS bands.
• Multi-dimensional attention mechanism (MDAM) is proposed.

Craniomaxillofacial (CMF) and nasal landmark detection are fundamental components in computer-assisted surgery. Medical landmark detection method includes regression-based and heatmap-based methods, and heatmap-based methods are among the main ...

• Two novel automatic heatmap-based landmark detection methods are proposed.
• The proposed super-resolution module effectively reduces localization errors.
• Integration of global knowledge and local features for representation ...

In recent years, Lightweight image super-resolution technology has achieved good performance. However, many models struggle to effectively capture and process global information, leading to problems such as loss of detail and unnatural texture in ...

Light field (LF) image super-resolution has always been a challenging task due to the complex structure of light field image, where spatial and angular information is highly coupled with varying disparities. Recent studies tend to disentangle a 4D ...

Iterative refinement based image super-resolution with conditional denoising diffusion probabilistic models (DDPM), such as SR3 [21], has shown promise in the super-resolution of magnetic resonance images (MRIs). However, these methods are ...

Digital pathology slides can serve medical practitioners or aid in computer-assisted diagnosis and treatment. Collection personnel typically employ hyperspectral microscopes to scan pathology slides into Whole Slide Images (WSI) with pixel counts ...