• Corpus ID: 5033954

Residual-Guide Feature Fusion Network for Single Image Deraining

@article{Fan2018ResidualGuideFF,
  title={Residual-Guide Feature Fusion Network for Single Image Deraining},
  author={Zhiwen Fan and Huafeng Wu and Xueyang Fu and Yue Huang and Xinghao Ding},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.07493}
}
Single image rain streaks removal is extremely important since rainy images adversely affect many computer vision systems. [] Key Method By using this strategy, we can obtain a coarse to fine estimation of negative residual as the blocks go deeper. The outputs of different blocks are merged into the final reconstruction.
Bilateral Recurrent Network for Single Image Deraining
TLDR
Bilateral recurrent network (BRN) to simultaneously exploit rain streak layer and background image layer is proposed and notably outperforms state-of-the-art deep deraining networks on both synthetic datasets and real rainy images.
Residual Squeeze-and-Excitation Network for Fast Image Deraining
TLDR
Experimental results demonstrate that the proposed residual squeeze-and-excitation network RSEN can not only considerably reduce the computational complexity but also significantly improve the deraining performance compared with state-of-the-art methods.
Single image rain streaks removal: a review and an exploration
TLDR
A specific coarse-to-fine deraining network architecture is built, which can finely deliver the rain structures and progressively removes rain streaks from the input image, accordingly, and possesses better generalization capability on real rainy images, implying its potential usefulness for this task.
Dual Recursive Network for Fast Image Deraining
TLDR
This paper proposes a dual recursive network (DRN) for fast image deraining as well as comparable or superior deraining performance compared with state-of-the-art approaches, utilizing a residual network with only 2 residual blocks, which is recursively unfolded to remove rain streaks in multiple stages.
Single Image Deraining Using Bilateral Recurrent Network
TLDR
Bilateral LSTMs are proposed, which not only can respectively propagate deep features of rain streak layer and background image layer across stages across stages, but also bring the interplay between these two SRNs, finally forming bilateral recurrent network (BRN).
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset
TLDR
A semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images is proposed, and a novel SPatial Attentive Network (SPANet) is proposed to remove rain streaks in a local-to-global manner.
Single Image Rain Removal via a Simplified Residual Dense Network
TLDR
This paper proposes a simplified residual dense network (SRDN) to improve the de-raining performance and cut down the computation time of network, inspired by the image processing domain knowledge that a rainy image can be decomposed into a base (low-pass) layer and a detail (high- pass) layer.
Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks
TLDR
This work proposes to utilize the generative capabilities of recently introduced conditional generative adversarial networks (cGANs) as an image de-raining approach by utilizing the adversarial loss in GANs that provides an additional component to the loss function, which in turn regulates the final output and helps to yield better results.
Rain Streak Removal for Single Image via Kernel Guided CNN
TLDR
A novel rain streak removal approach using a kernel guided convolutional neural network (KGCNN), achieving the state-of-the-art performance with simple network architectures is proposed.
...
1
2
3
...

References

SHOWING 1-10 OF 33 REFERENCES
Removing Rain from Single Images via a Deep Detail Network
TLDR
A deep detail network is proposed to directly reduce the mapping range from input to output, which makes the learning process easier and significantly outperforms state-of-the-art methods on both synthetic and real-world images in terms of both qualitative and quantitative measures.
Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal
We introduce a deep network architecture called DerainNet for removing rain streaks from an image. Based on the deep convolutional neural network (CNN), we directly learn the mapping relationship
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.
Image De-Raining Using a Conditional Generative Adversarial Network
TLDR
This work attempts to leverage powerful generative modeling capabilities of the recently introduced conditional generative adversarial networks (CGAN) by enforcing an additional constraint that the de-rained image must be indistinguishable from its corresponding ground truth clean image.
DehazeNet: An End-to-End System for Single Image Haze Removal
TLDR
This paper proposes a trainable end-to-end system called DehazeNet, for medium transmission estimation, which takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model.
Deep Joint Rain Detection and Removal from a Single Image
TLDR
A recurrent rain detection and removal network that removes rain streaks and clears up the rain accumulation iteratively and progressively is proposed and a new contextualized dilated network is developed to exploit regional contextual information and to produce better representations for rain detection.
Multi-Scale Dense Networks for Resource Efficient Image Classification
TLDR
Experiments demonstrate that the proposed framework substantially improves the existing state-of-the-art in both image classification with computational resource limits at test time and budgeted batch classification.
Single Image Dehazing via Multi-scale Convolutional Neural Networks
TLDR
A multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines results locally.
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.
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.
...
1
2
3
4
...