Blind Super-Resolution With Iterative Kernel Correction

@article{Gu2019BlindSW,
  title={Blind Super-Resolution With Iterative Kernel Correction},
  author={Jinjin Gu and Hannan Lu and Wangmeng Zuo and Chao Dong},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={1604-1613}
}
  • Jinjin Gu, Hannan Lu, +1 author Chao Dong
  • Published 6 April 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Deep learning based methods have dominated super-resolution (SR) field due to their remarkable performance in terms of effectiveness and efficiency. [...] Key Method We draw the observation that kernel mismatch could bring regular artifacts (either over-sharpening or over-smoothing), which can be applied to correct inaccurate blur kernels. Thus we introduce an iterative correction scheme -- IKC that achieves better results than direct kernel estimation.Expand
Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution
TLDR
This paper proposes a novel blind SR framework to super-resolve LR images degraded by arbitrary blur kernel with accurate kernel estimation in frequency domain, and is the first deep learning method which conducts blur kernel estimationIn frequency domain. Expand
Blind Super-Resolution with Kernel-Aware Feature Refinement
TLDR
A new kernel predictor (KP) is proposed to predict the blur kernel from the input low-resolution image and the kernel-aware feature refinement (KAFR) module is designed to utilize the predicted blur kernel to facilitate the restoration of the high- resolution image. Expand
KernelNet: A Blind Super-Resolution Kernel Estimation Network
TLDR
The proposed model outperforms the state-of-the-art SR kernel estimator, KernelGAN, by a significant margin in SR kernel reconstruction accuracy and is the first one that can estimate the SR kernel in real-time by performing O(1k) times faster than KernelGAN. Expand
Semi-Blind Super-Resolution with Kernel-Guided Feature Modification
TLDR
A semi-blind super-resolution method where the blur kernel is unknown, which achieves superior performance in the blind SR problem and follows the meta-learning and design the Meta Feature Modification module to modify the image features. Expand
Temporal Kernel Consistency for Blind Video Super-Resolution
  • Lichuan Xiang, Royson Lee, M. Abdelfattah, N. Lane, Hongkai Wen
  • Computer Science, Engineering
  • 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
  • 2021
TLDR
The temporal properties of the kernels are investigated and its importance in the task of blind video super-resolution is highlighted, achieving the new state-of-the-art in blind video SR and underlining the potential of exploiting kernel temporal consistency. Expand
Blind Super-Resolution Kernel Estimation using an Internal-GAN
TLDR
KernelGAN is introduced, an image-specific Internal-GAN, which trains solely on the LR test image at test time, and learns its internal distribution of patches, and leads to state-of-the-art results in Blind-SR when plugged into existing SR algorithms. Expand
End-to-end Alternating Optimization for Blind Super Resolution
TLDR
This work designs two convolutional neural modules, namely Restorer and Estimator, which can estimate the blur kernel and restore the SR image in a single model and can largely outperform state-of-the-art methods and produce more visually favorable results at a much higher speed. Expand
Real-World Super-Resolution via Kernel Estimation and Noise Injection
TLDR
This work designs a novel degradation framework for real-world images by estimating various blur kernels as well as real noise distributions and proposes a real- world super-resolution model aiming at better perception. Expand
Learning the Non-differentiable Optimization for Blind Super-Resolution
TLDR
An adaptive modulation network (AMNet) for multiple degradations SR is proposed, which is composed of the pivotal adaptive modulation layer (AMLayer) which is an efficient yet lightweight fusion layer between blur kernel and image features. Expand
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
TLDR
Extensive experiments show that the proposed MANet not only performs favorably for both spatially variant and invariant kernel estimation, but also leads to state-of-the-art blind SR performance when combined with non-blind SR methods. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 42 REFERENCES
Conditioned Regression Models for Non-blind Single Image Super-Resolution
TLDR
This paper proposes conditioned regression models (including convolutional neural networks and random forests) that can effectively exploit the additional kernel information during both, training and inference and empirically shows that they can effectively handle scenarios where the blur kernel is different for each image. Expand
Nonparametric Blind Super-resolution
  • T. Michaeli, M. Irani
  • Mathematics, Computer Science
  • 2013 IEEE International Conference on Computer Vision
  • 2013
TLDR
It is shown that recurrence of small patches across scales of the low-res image (which forms the basis for single-image SR), can also be used for estimating the optimal blur kernel, which leads to significant improvement in SR results. Expand
A soft MAP framework for blind super-resolution image reconstruction
TLDR
A new soft maximum a posteriori (MAP) estimation framework to perform joint blur identification and HR image reconstruction that incorporates a soft blur prior that estimates the relevance of the best-fit parametric blur model, and induces reinforcement learning towards it. Expand
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. Expand
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
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. Expand
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. Expand
Accelerating the Super-Resolution Convolutional Neural Network
TLDR
This paper aims at accelerating the current SRCNN, and proposes a compact hourglass-shape CNN structure for faster and better SR, and presents the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. Expand
Image Super-Resolution Using Deep Convolutional Networks
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deepExpand
Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform
TLDR
It is shown that it is possible to recover textures faithful to semantic classes in a single network conditioned on semantic segmentation probability maps through a novel Spatial Feature Transform (SFT) layer that generates affine transformation parameters for spatial-wise feature modulation. Expand
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
TLDR
This paper presents the first convolutional neural network capable of real-time SR of 1080p videos on a single K2 GPU and introduces an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. Expand
...
1
2
3
4
5
...