Attention Mechanism Enhanced Kernel Prediction Networks for Denoising of Burst Images

@article{Zhang2020AttentionME,
  title={Attention Mechanism Enhanced Kernel Prediction Networks for Denoising of Burst Images},
  author={Bin Zhang and Shenyao Jin and Yili Xia and Yongming Huang and Zixiang Xiong},
  journal={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2020},
  pages={2083-2087}
}
  • Bin Zhang, Shenyao Jin, +2 authors Z. Xiong
  • Published 18 October 2019
  • Computer Science, Engineering
  • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Deep learning based image denoising methods have been extensively investigated. In this paper, attention mechanism enhanced kernel prediction networks (AME-KPNs) are proposed for burst image denoising, in which, nearly cost-free attention modules are adopted to first refine the feature maps and to further make a full use of the inter-frame and intra-frame redundancies within the whole image burst. The proposed AME-KPNs output per-pixel spatially-adaptive kernels, residual maps and corresponding… Expand
Weighted Multi-Kernel Prediction Network for Burst Image Super-Resolution
TLDR
This paper proposes a novel weighted multi-kernel prediction network (WMKPN) that can learn the discriminative features on each pixel for burst image super-resolution and demonstrates that WMKPN improves the visual quality of super-resolved images. Expand
Underwater Image Enhancement Based on Multi-Scale Spatial and Channel Attention Fusion
Degraded underwater image enhancement is a challenging task. Due to the light scattering and absorption of suspended particles in water, the original underwater image has a low definition, blurredExpand
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
TLDR
The NTIRE2021 challenge on burst super-resolution was to generate a clean RGB image with 4 times higher resolution given a RAW noisy burst as input, and the top-performing methods set a new state-of-the-art for the burstsuper-resolution task. Expand
Deep Learning on Image Denoising: An overview
TLDR
A comparative study of deep techniques in image denoising by classifying the deep convolutional neural networks for additive white noisy images, the deep CNNs for real noisy images; the deepCNNs for blind Denoising and the deep network for hybrid noisy images. Expand

References

SHOWING 1-10 OF 21 REFERENCES
Multi-Kernel Prediction Networks for Denoising of Burst Images
TLDR
A deep neural network based approach called Multi-Kernel Prediction Networks (MKPN) for burst image denoising which predicts kernels of not just one size but of varying sizes and performs fusion of these different kernels resulting in one kernel per pixel. Expand
Real Image Denoising With Feature Attention
  • Saeed Anwar, N. Barnes
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
A novel single-stage blind real image denoising network (RIDNet) is proposed by employing a modular architecture that uses residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Expand
Learning Deformable Kernels for Image and Video Denoising
TLDR
This work proposes deformable 2D kernels for image denoising where the sampling locations and kernel weights are both learned and develops 3D deformable kernels for video Denoising to more efficiently sample pixels across the spatial-temporal space. Expand
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TLDR
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance. Expand
Burst Denoising with Kernel Prediction Networks
TLDR
A convolutional neural network architecture for predicting spatially varying kernels that can both align and denoise frames, a synthetic data generation approach based on a realistic noise formation model, and an optimization guided by an annealed loss function to avoid undesirable local minima are proposed. Expand
End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks
TLDR
A recurrent fully convolutional network (RFCN) to process burst photos taken under extremely low-light conditions, and to obtain denoised images with improved brightness is proposed. Expand
CBAM: Convolutional Block Attention Module
TLDR
The proposed Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks, can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. Expand
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
TLDR
This paper proposes to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum, making training deep networks easier and achieving restoration performance gains consequently. Expand
GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-Based Real-World Noise Modeling
TLDR
A grouped residual dense network (GRDN) is proposed, which is an extended and generalized architecture of the state-of-the-art residual densenetwork (RDN) and a new generative adversarial network-based real-world noise modeling method is developed. Expand
Toward Convolutional Blind Denoising of Real Photographs
TLDR
A convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs and a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Expand
...
1
2
3
...