Implicit Euler ODE Networks for Single-Image Dehazing

@article{Shen2020ImplicitEO,
  title={Implicit Euler ODE Networks for Single-Image Dehazing},
  author={Jiawei Shen and Zhuoyan Li and Lei Yu and Guisong Xia and Wen Yang},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2020},
  pages={877-886}
}
  • Jiawei Shen, Zhuoyan Li, +2 authors Wen Yang
  • Published 1 June 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem. Recently, many works indicate that the ResNet can be considered as the explicit Euler forward approximation of an ordinary differential equation (ODE). In this paper, we extend the explicit forward approximation to the implicit backward counterpart, which can be realized via a recursive neural… Expand
Single Image Dehazing Using End-to-End Deep-Dehaze Network
TLDR
The proposed Deep-Dehaze architecture surpasses previous state-of-the-art single image dehazing methods quantitatively and qualitatively and achieves outstanding average PSNR score 24.5 on the RESIDE dataset. Expand
Single Image Dehazing Using End-to-End Deep-Dehaze Network
TLDR
This study offers the Deep-Dehaze network to retrieve haze-free images by training the image translation and dehazing network in an end-to-end manner and validated it on natural and synthetic hazy datasets. Expand
A Framework for Objective Evaluation of Single Image De-Hazing Techniques
TLDR
A general methodology is introduced, as a framework for objective performance evaluation of current and future dehazing tasks, through an extensive comparison of 15 single image de-hazing techniques over a vast range of image data sets. Expand
MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning
TLDR
This work regards the gradient itself as meta-knowledge and then proposes a novel prototype optimization-based meta-learning framework, called MetaNODE, which first regard the mean-based prototypes as initial prototypes, and then model the process of prototype optimization as continuous-time dynamics specified by a Neural Ordinary Differential Equation (Neural ODE). Expand

References

SHOWING 1-10 OF 46 REFERENCES
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. Expand
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
TLDR
An end-to-end trainable Convolutional Neural Network for single image dehazing, named GridDehazeNet, which implements a novel attention-based multi-scale estimation on a grid network, and an explanation as to why it is not necessarily beneficial to take advantage of the dimension reduction offered by the atmosphere scattering model. Expand
AOD-Net: All-in-One Dehazing Network
TLDR
An image dehazing model built with a convolutional neural network (CNN) based on a re-formulated atmospheric scattering model, called All-in-One Dehazing Network (AOD-Net), which demonstrates superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Expand
Deep Multi-Model Fusion for Single-Image Dehazing
  • Zijun Deng, Lei Zhu, +5 authors P. Heng
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
TLDR
A deep multi-model fusion network to attentively integrate multiple models to separate layers and boost the performance in single-image dehazing is presented. Expand
Gated Fusion Network for Single Image Dehazing
TLDR
An efficient algorithm to directly restore a clear image from a hazy input using an end-to-end trainable neural network that consists of an encoder and a decoder is proposed. Expand
Gated Context Aggregation Network for Image Dehazing and Deraining
TLDR
An end-to-end gated context aggregation network to directly restore the final haze-free image by adopting the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters. Expand
Single Image Dehazing via Conditional Generative Adversarial Network
TLDR
This paper proposes an algorithm to directly restore a clear image from a hazy image based on a conditional generative adversarial network (cGAN), where the clear image is estimated by an end-to-end trainable neural network. Expand
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. Expand
Densely Connected Pyramid Dehazing Network
  • H. Zhang, Vishal M. Patel
  • Computer Science, Engineering
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
A new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazed all together by directly embedding the atmospheric scattering model into the network. Expand
Understanding Convolution for Semantic Segmentation
TLDR
DUC is designed to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling, and a hybrid dilated convolution (HDC) framework in the encoding phase is proposed. Expand
...
1
2
3
4
5
...