Dual Reconstruction with Densely Connected Residual Network for Single Image Super-Resolution

Hsu, Chih–Chung; Lin, Chia-Hsiang

doi:10.1109/iccvw.2019.00449

Cited by 10 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the medical images collected by instruments with different parameters have certain deviations. Furthermore, this paper uses the Evaluation indicators RIED-Net [5] pix2pix [7] Reset GAN [11] pGAN [15] Residual U-Net GAN [17] Proposed algorithm same preprocessing steps to process all data. Therefore, the data collection method and preprocessing method will have a particular impact on the experimental results.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

CNN-Based Cross-Modal Residual Network for Image Synthesis

Kumar

Bhatnagar

Jain

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

This study attempts to address the issue that present cross-modal image synthesis algorithms do not capture the spatial and structural information of human tissues effectively. As a consequence, the resulting photos include flaws including fuzzy edges and a poor signal-to-noise ratio. The authors offer a cross-sectional technique that combines residual modules with generative adversarial networks. The approach incorporates an enhanced residual initial module and attention mechanism into the generator network, reducing the number of parameters and improving the generator’s feature learning capabilities. To boost discriminant performance, the discriminator employs a multiscale discriminator. A multilevel structural similarity loss is included in the loss function to improve picture contrast preservation. On the ADNI data set, the algorithm is compared to the mainstream algorithms. The experimental findings reveal that the synthetic PET image’s MAE index has dropped while the SSIM and PSNR indexes have improved. The experimental findings suggest that the proposed model may maintain picture structural information while improving image quality in both visual and objective measures. The residue initial module and attention mechanism are employed to increase the generator’s capacity for learning, while the multiscale discriminator is utilized to improve the model’s discriminative performance. The enhanced method in this study can maintain the structure and contrast information of the picture, according to comparative experimental findings using the ADNI dataset. The produced picture is hence more aesthetically similar to the genuine print.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Module. [11] proposed an attention module for medical images; the structure is shown in Figure 2. The attention mechanism determines the attention coefficients of different regions on each input x l by gating the signal g, allowing the network to focus on areas more relevant to the task and suppress irrelevant background regions.…”

Section: Attentionmentioning

confidence: 99%

CNN-Based Cross-Modal Residual Network for Image Synthesis

Kumar

Bhatnagar

Jain

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…Liu et al [41] introduced residual feature aggreation (RFA) network that fused all the features from residual block through dense connection to gather all the information without losing it. A similar technique was also found in the densely connected residual network (DCRN) proposed by Hsu et al [42].…”

Section: Related Workmentioning

confidence: 76%

Enhanced Dense Space Attention Network for Super-Resolution Construction From Single Input Image

2021

View full text Add to dashboard Cite

In some applications, such as surveillance and biometrics, image enlargement is required to inspect small details on the image. One of the image enlargement approaches is by using convolutional neural network (CNN)-based super-resolution construction from a single image. The first CNN-based image superresolution algorithm is the super-resolution CNN (SRCNN) developed in 2014. Since then, many researchers have proposed several versions of CNN-based algorithms for image super-resolution to improve the accuracy or reduce the model's running time. Currently, some algorithms still suffered from the vanishing-gradient problem and relied on a large number of layers. Thus, the motivation of this work is to reduce the vanishinggradient problem that can improve the accuracy, and at the same time, reduce the running time of the model. In this paper, an enhanced dense space attention network (EDSAN) model is proposed to overcome the problems. The EDSAN model adopted a dense connection and residual network to utilize all the features to correlate the low-level feature and high-level feature as much as possible. Besides, implementing the convolution block attention module (CBAM) layer and multiscale block (MSB) helped reduce the number of layers required to achieve comparable results. The model is evaluated through peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) metrics. EDSAN achieved the most significant improvement, about 1.42% when compared to the CRN model using the Set5 dataset at a scale factor of 3. Compared to the ERN model, EDSAN performed the best, with a 1.22% improvement made when using the Set5 dataset at a scale factor of 4. In terms of overall performance, EDSAN performed very well in all datasets at a scale factor of 2 and 3. In conclusion, EDSAN successfully solves the problems above, and it can be used in different applications such as biometric identification applications and real-time video applications.

show abstract

“…In the face of some other potential challenges, we do not think it is suitable to use NeRF-based methods to solve them. For example, in the face of low resolution, some super-resolution reconstruction methods [11] can be used, and in the face of image distortion caused by the camera, there are also some distortion correction methods [12].…”

Section: Introductionmentioning

confidence: 99%

STs-NeRF: Novel View Synthesis of Space Targets Based on Improved Neural Radiance Fields

Ma,

Liu,

Sun

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Since Neural Radiation Field (NeRF) was first proposed, a large number of studies dedicated to them have emerged. These fields achieved very good results in their respective contexts, but they are not sufficiently practical for our project. If we want to obtain novel images of satellites photographed in space by another satellite, we must face problems like inaccurate camera focal lengths and poor image texture. There are also some small structures on satellites that NeRF-like algorithms cannot render well. In these cases, the NeRF’s performance cannot sufficiently meet the project’s needs. In fact, the images rendered by the NeRF will have many incomplete structures, while the MipNeRF will blur the edges of the structures on the satellite and obtain unrealistic colors. In response to these problems, we proposed STs-NeRF, which improves the quality of the new perspective images through an encoding module and a new network structure. We found a method for calculating poses that are suitable for our dataset and that enhance the network’s input learning effect by recoding the sampling points and viewing directions through a dynamic encoding (DE) module. Then, we input them into our layer-by-layer normalized multi-layer perceptron (LLNMLP). By simultaneously inputting points and directions into the network, we avoid the mutual influence between light rays, and through layer-by-layer normalization, we ease the model’s overfitting from a training perspective. Since real images should not be made public, we created a synthetic dataset and conducted a series of experiments. The experiments showed that our method achieves the best results in reconstructing captured satellite images, compared with the NeRF, the MipNeRF, the NeuS and the NeRF2Mesh, and improves the Peak Signal-to-Noise Ratio (PSNR) by 19%. We have also tested on public datasets, and our NeRF can still render acceptable images on datasets with better textures.

show abstract

Dual Reconstruction with Densely Connected Residual Network for Single Image Super-Resolution

Cited by 10 publications

References 25 publications

CNN-Based Cross-Modal Residual Network for Image Synthesis

CNN-Based Cross-Modal Residual Network for Image Synthesis

Enhanced Dense Space Attention Network for Super-Resolution Construction From Single Input Image

STs-NeRF: Novel View Synthesis of Space Targets Based on Improved Neural Radiance Fields

Contact Info

Product

Resources

About