DN-ResNet: Efficient Deep Residual Network for Image Denoising

@article{Ren2018DNResNetED,
  title={DN-ResNet: Efficient Deep Residual Network for Image Denoising},
  author={Haoyu Ren and Mostafa El-Khamy and Jungwon Lee},
  journal={ArXiv},
  year={2018},
  volume={abs/1810.06766}
}
A deep learning approach to blind denoising of images without complete knowledge of the noise statistics is considered. [] Key Method An edge-aware loss function is further utilized in training DN-ResNet, so that the denoising results have better perceptive quality compared to conventional loss function. Next, we introduce the depthwise separable DN-ResNet (DS-DN-ResNet) utilizing the proposed Depthwise Seperable ResBlock (DS-ResBlock) instead of standard ResBlock, which has much less computational cost.

DRFENet: Toward a residual network of dilated convolution for image denoising

: Deep learning technology dominates current research in image denoising. However, denoising performance is limited by target noise feature loss from information propagation in association with the

A Residual Dense U-Net Neural Network for Image Denoising

TLDR
This work presents a residual dense neural network (RDUNet) for image denoising based on the densely connected hierarchical network that consists of densely connected convolutional layers to reuse the feature maps and local residual learning to avoid the vanishing gradient problem and speed up the learning process.

Real Image Restoration via Structure-preserving Complementarity Attention

TLDR
A novel lightweight Complementary Attention Module is proposed, which includes a density module and a sparse module, which can cooperatively mine dense and sparse features for feature complementary learning to build an efficient lightweight architecture.

Considering Image Information and Self-similarity: A Compositional Denoising Network

TLDR
A compositional denoising network (CDN) is proposed, whose image information path (IIP) and noise estimation path (NEP) will solve the two problems, respectively, of residual learning.

Image Denoising for Strong Gaussian Noises With Specialized CNNs for Different Frequency Components

TLDR
Results of the proposed method show higher peak signal to noise ratio (PSNR), and structural similarity index (SSIM) compared to a popular state of the art denoising method in the presence of strong noises.

When AWGN-based Denoiser Meets Real Noises

TLDR
This paper proposes a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN, and investigates Pixel-shuffle Down-sampling strategy to adapt the trained model to real noises.

Exploring Efficient and Tunable Convolutional Blind Image Denoising Networks

TLDR
This work proposes to develop denoising networks that are tunable to achieve a desired balance between image quality and model size and seeks inspiration from architectures that are tuned for classification, detection, and semantic segmentation on mobile phone CPUs.

A Survey on the New Generation of Deep Learning in Image Processing

TLDR
This survey provides four deep learning model series, which includes CNN series, GAN series, ELM-RVFL series, and other series, for comprehensive understanding towards the analytical techniques of image processing field, clarify the most important advancements and shed some light on future studies.

A Multi-Head Convolutional Neural Network With Multi-path Attention improves Image Denoising

TLDR
A novel CNN with multiple heads (MH) named MHCNN is proposed in this paper, whose heads will receive the input images rotated by different rotation angles, and a novel multi-path attention mechanism (MPA) to integrate these features effectively.

Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding

TLDR
A two-stage robust SIDE framework that can perform blind SIDE for both indoor and outdoor scenes is proposed and achieves the top performance compared to the Robust Vision Challenge (ROB) 2018 submissions.

References

SHOWING 1-10 OF 27 REFERENCES

Image Super-Resolution via Deep Recursive Residual Network

TLDR
This paper proposes a very deep CNN model (up to 52 convolutional layers) named Deep Recursive Residual Network (DRRN) that strives for deep yet concise networks, and recursive learning is used to control the model parameters while increasing the depth.

FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising

TLDR
The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance, and enjoys several desirable properties, including the ability to handle a wide range of noise levels effectively with a single network.

CT-SRCNN: Cascade Trained and Trimmed Deep Convolutional Neural Networks for Image Super Resolution

TLDR
A cascade training approach to deep learning is proposed to improve the accuracy of the neural networks while gradually increasing the number of network layers, and two methodologies, the one-shot trimming and the cascade trimming, are proposed.

Deep class-aware image denoising

TLDR
It is shown that a significant boost in performance of up to 0.4dB PSNR can be achieved by making the network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class.

MemNet: A Persistent Memory Network for Image Restoration

TLDR
A very deep persistent memory network (MemNet) is proposed that introduces a memory block, consisting of a recursive unit and a gate unit, to explicitly mine persistent memory through an adaptive learning process.

Deep Residual Learning for Image Recognition

TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Deep Convolutional Denoising of Low-Light Images

TLDR
This paper demonstrates how by training the same network with images having a specific peak value, the denoiser outperforms previous state-of-the-art by a large margin both visually and quantitatively.

Full Resolution Image Compression with Recurrent Neural Networks

TLDR
This is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.

Image Super Resolution Based on Fusing Multiple Convolution Neural Networks

TLDR
Using SRCNN as individual network, the CNF network achieves the state-of-the-art accuracy on benchmark image datasets and fine-tuning the whole fused network improves the accuracy.

Lossy Image Compression with Compressive Autoencoders

TLDR
It is shown that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs, and furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images.