Light-field spatial super-resolution via enhanced spatial-angular separable convolutional network

Hua, Xiyao; Wang, Minghui; Su, Boni

doi:10.1117/1.jei.31.5.053030

Cited by 2 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shallow features mainly contain low-level information, and the deep features focus on recovering lost high-level information. 29 Through the residual skip connection, the model can transfer the features directly to the IR module. The IR module employs the subpixel convolution layer 30 for upsampling.…”

Section: Vision Transformermentioning

confidence: 99%

Attention-guided hybrid transformer-convolutional neural network for underwater image super-resolution

Zhan,

Li,

Zhang

2024

J. Electron. Imag.

View full text Add to dashboard Cite

Underwater images suffer from localized distortion and blurred degradation of edge structures due to light absorption and scattering by water. However, existing superresolution (SR) methods for underwater images cannot effectively solve the above problems and encounter model sizes that are too large. To this end, we propose an attention-guided hybrid transformer-CNN network (AHTCN) to improve the SR reconstruction of underwater images through the interaction of local and multiscale global information, as well as the long-range dependencies modeling capability. Specifically, AHTCN mainly consists of several cascaded transformer-CNN feature extraction blocks (TCFEB) and an image reconstruction module. In TCFEB, the designed attention-based channel separation mechanism can adaptively separate the weighted features while reducing the number of model parameters and then extract the local details and global structural information at different scales through the dual-stream structure. Moreover, we replace the feedforward layer in the transformer with the blueprint separable convolutional feedforward layer and propose an enhanced pyramid pooling transformer layer, which helps to strengthen the feature perception of the model. Experimental results demonstrate that AHTCN outperforms the state-of-the-art algorithms in terms of both subjective visual effects and objective quality assessment, while requiring fewer parameters.

show abstract

Section: Vision Transformermentioning

confidence: 99%

Attention-guided hybrid transformer-convolutional neural network for underwater image super-resolution

Zhan,

Li,

Zhang

2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…presented an image SR method based on an attention mechanism feedback network, making better use of the expressive ability of deep learning networks. Hua et al 18 . designed an efficient neural network for light-field spatial super-resolution, in which repeatedly alternating spatial and angular domains can fully exploit the spatial and angular information.…”

Section: Related Workmentioning

confidence: 99%

Single-image super-resolution via dynamic multi-task learning and multi-level mutual feature fusion

et al. 2023

View full text Add to dashboard Cite

In recent years, deep neural networks have exhibited promising performance in the single-image super-resolution (SISR) task by designing complex network structures from the low-resolution (LR) images to the high-resolution (HR) images and learning the mapping function. However, the SISR task is a widely known ill-posed problem. Since it may map one LR image input to multiple HR images, there are always undesired structural distortions in the recovered SR images. We creatively propose a SISR network with dynamic multi-task learning and multi-level mutual feature fusion (DMMFSR), alleviating structural distortion problems while maintaining more edge structure. Specifically, we utilize a DML block (DMLB) to train low-frequency and high-frequency image information extraction networks so the two networks can mutually promote each other. In addition, we also use a multi-level mutual feature fusion block to fuse image and edge features at different levels. Extensive experiments demonstrate the effectiveness of our proposed DMMFSR. Meanwhile, our model achieves comparable peak signal-to-noise ratio and structural similarity scores on multiple SR benchmarks compared with state-of-the-art SR methods.

show abstract

Light-field spatial super-resolution via enhanced spatial-angular separable convolutional network

Cited by 2 publications

References 42 publications

Attention-guided hybrid transformer-convolutional neural network for underwater image super-resolution

Attention-guided hybrid transformer-convolutional neural network for underwater image super-resolution

Single-image super-resolution via dynamic multi-task learning and multi-level mutual feature fusion

Contact Info

Product

Resources

About