Progressive Perception-Oriented Network for Single Image Super-Resolution

@article{Hui2021ProgressivePN,
  title={Progressive Perception-Oriented Network for Single Image Super-Resolution},
  author={Zheng Hui and Jie Li and Xinbo Gao and Xiumei Wang},
  journal={Inf. Sci.},
  year={2021},
  volume={546},
  pages={769-786}
}
View PDF on arXiv
View With Semantic Reader
20 Citations
Highly Influential Citations
1
Background Citations
2
Methods Citations
7

20 Citations

Citation Type

Citation Type

Single Image Super-Resolution Using Depth Map as Constraint
TLDR
A self-adaptive feature transform (AFT) layer, which can perform affine transformation on the feature map based on the depth map to constrain the plausible solution space of the SR image, and a hierarchical residual multi-scale fusion block to improve the representational ability of the network are proposed.
Multi-Step Reinforcement Learning for Single Image Super-Resolution
TLDR
This research applies a multi-agent Reinforcement Learning (RL) algorithm to SISR, creating an advanced ensemble approach for combining powerful GANs, particularly using Generative Adversarial Networks.
Flexible Style Image Super-Resolution Using Conditional Objective
TLDR
This work optimize an SR model with a conditional objective during training, where the objective is a weighted sum of multiple perceptual losses at different feature levels, and presents an architecture appropriate for this training scheme, which is the Residual-in-Residual Dense Block equipped with spatial feature transformation layers.
Progressive face super-resolution with cascaded recurrent convolutional network
Deformable Non-Local Network for Video Super-Resolution
TLDR
This paper applies the deformable convolution and improves its ability of adaptive alignment at the feature level and utilizes a non-local structure to capture the global correlation between the reference frame and the aligned neighboring frames, and simultaneously enhance desired fine details in the aligned frames.
A multi-objective opposition-based barnacles mating optimization for image super resolution using hyper-Spectral images
TLDR
This paper adopts a latest optimization algorithm called O-BMO with optimized Non-negative Structured Sparse Representation (NSSR), Adaptive Discrete Wavelet Transform (ADWT) and Optimized Deep Convolutional Neural Network for developing the enhanced image super-resolution model.
Enhancing Multi-Scale Implicit Learning in Image Super-Resolution with Integrated Positional Encoding
TLDR
This work proposes integrated positional encoding (IPE), extending traditional positional encoding by aggregating frequency information over the pixel area by applying IPE to the state-of-the-art arbitrary-scale image super-resolution method: local implicit image function (LIIF), presenting IPE-LIIf.
Small Object Detection in Remote Sensing Images with Residual Feature Aggregation-Based Super-Resolution and Object Detector Network
TLDR
A rationale for image super- resolution for small objects by improving the current super-resolution (SR) framework by incorporating a cyclic generative adversarial network (GAN) and residual feature aggregation (RFA) to improve detection performance is provided.
VIRTUAL RESTORATION OF MISSING PAINT LOSS OF MURAL BASED ON GENERATIVE ADVERSARIAL NETWORK
  • Q. Wang, M. Hou, S. Lyu
  • Computer Science
    The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • 2021
TLDR
A fine image restoration network model based on generative adversarial network which can effectively restore the lines and faces in the murals and is conducive to the appreciation and display of murals is constructed.
Neural Network-Based Ultra-High-Definition Video Live Streaming Optimization Algorithm
TLDR
An image superresolution algorithm based on hybrid dilated convolution and Laplacian pyramid is proposed, which outperforms baselines with respect to peak signal to noise ratio (PSNR), structural similarity index measurement (SSIM), and image quality.
...
1
2
...

References

SHOWING 1-10 OF 53 REFERENCES
SRFeat: Single Image Super-Resolution with Feature Discrimination
TLDR
A novel GAN-based SISR method that overcomes the limitation and produces more realistic results by attaching an additional discriminator that works in the feature domain and design a new generator that utilizes long-range skip connections so that information between distant layers can be transferred more effectively.
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
TLDR
This work proposes a novel application of automated texture synthesis in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixelaccurate reproduction of ground truth images during training to achieve a significant boost in image quality at high magnification ratios.
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
  • K. Zhang, W. Zuo, Lei Zhang
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
Extensive experimental results show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
TLDR
This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN.
Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
TLDR
This paper proposes the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images and generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications.
Multi-scale Residual Network for Image Super-Resolution
TLDR
A novel multi-scale residual network (MSRN) to fully exploit the image features, which outperform most of the state-of-the-art methods.
Feedback Network for Image Super-Resolution
TLDR
An image super-resolution feedback network (SRFBN) is proposed to refine low-level representations with high-level information by using hidden states in a recurrent neural network (RNN) with constraints to achieve such feedback manner.
Enhanced Deep Residual Networks for Single Image Super-Resolution
TLDR
This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model.
...
1
2
3
4
5
...